Seattle is looking to celebrate and accelerate its leadership in artificial intelligence at the very moment the first wave of the AI economy is crashing down on the region’s tech workforce.

That contrast was hard to miss Monday evening at the opening reception for Seattle AI Week 2025 at Pier 70. On stage, panels offered a healthy dose of optimism about building the AI future. In the crowd, buzz about Amazon’s impending layoffs brought the reality of the moment back to earth.

A region that rose with Microsoft and then Amazon is now dealing with the consequences of Big Tech’s AI-era restructuring. Companies that hired by the thousands are now thinning their ranks in the name of efficiency and focus — a dose of corporate realism for the local tech economy.

The double-edged nature of this shift is not lost on Washington Gov. Bob Ferguson.

“AI, and the future of AI, and what that means for our state and the world — each day I do this job, the more that moves up in my mind in terms of the challenges and the opportunities we have,” Ferguson told the AI Week crowd. He touted Washington’s concentration of AI jobs, saying his goal is to maximize the benefits of AI while minimizing its downsides.

Seattle AI Week, led by the Washington Technology Industry Association, was started last year after a Forbes list of the nation’s top 50 AI startups included none from Seattle, said the WTIA’s Nick Ellingson, opening this year’s event. That didn’t seem right. Was it a messaging problem?

“A bunch of us got together and said, let’s talk about all the cool things happening around AI in Seattle, and let’s expand the tent beyond just tech things that are happening,” Ellingson explained.

So maybe that’s the best measuring stick: how many startups will this latest shakeout spark, and how can the Seattle region’s startup and tech leaders make it happen? Can the region become less dependent on the whims of the Microsoft and Amazon C-suites in the process? 

“Washington has so much opportunity. It’s one of the few capitals of AI in the world,” said WTIA’s Arry Yu in her opening remarks. “People talk about China, people talk about Silicon Valley — there are a few contenders, but really, it’s here in Seattle. … The future is built on data, on powerful technology, but also on community. That’s what makes this place different.”

And yet, “AI is a sleepy scene in Seattle, where people work at their companies, but there’s very little activity and cross-pollinating outside of this,” said Nathan Lambert, senior research scientist with the Allen Institute for AI, during the opening panel discussion.

No, we don’t want to become San Francisco or Silicon Valley, Lambert added. But that doesn’t mean the region can’t cherry-pick some of the ingredients that put Bay Area tech on top.

Whether laid-off tech workers will start their own companies is a common question after layoffs like this. In the Seattle region at least, that outcome has been more fantasy than reality. 

This is where AI could change things, if not with the fabled one-person unicorn then with a bigger wave of new companies born of this employment downturn. Who knows, maybe one will even land on that elusive Forbes AI 50 list. (Hey, a region can dream!)

But as the new AI reality unfolds in the regional workforce, maybe the best question to ask is whether Seattle’s next big thing can come from its own backyard again.

Microsoft and OpenAI announced the long-awaited details of their new partnership agreement Tuesday morning — with concessions on both sides that keep the companies aligned but not in lockstep as they move into their next phases of AI development.

Under the arrangement, Microsoft gets a 27% equity stake in OpenAI’s new for-profit entity, the OpenAI Group PBC (Public Benefit Corporation), a stake valued at approximately $135 billion. That’s a decrease from 32.5% equity but not a bad return on an investment of $13.8 billion.

At the same time, OpenAI has contracted to purchase an incremental $250 billion in Microsoft Azure cloud services. However, in a significant concession in return for that certainty, Microsoft will no longer have a “right of first refusal” on new OpenAI cloud workloads.

Microsoft, meanwhile, will retain its intellectual property rights to OpenAI models and products through 2032, an extension of the timeframe that existed previously. 

A key provision of the new agreement centers on Artificial General Intelligence (AGI), with any declaration of AGI by OpenAI now subject to verification by an independent expert panel. This was a sticking point in the earlier partnership agreement, with an ambiguous definition of AI potentially triggering new provisions of the prior arrangement. 

Microsoft and OpenAI had previously announced a tentative agreement without providing details. More aspects of the deal are disclosed in a joint blog post from the companies.

Shares of Microsoft are up 2% in early trading after the announcement. The company reports earnings Wednesday afternoon, and some analysts have said the uncertainty over the OpenAI arrangement has been impacting Microsoft’s stock. 

A new report exploring the potential for the Pacific Northwest to stake its claim as the global leader in responsible AI offers a paradoxical view. The Cascadia region, which includes Seattle, Portland and Vancouver, B.C., is described as a proven, promising player in the sphere — but with significant risks that threaten its success.

“We created companies that transformed global commerce,” writes former Gov. Chris Gregoire in a forward to the document. “Now we have the chance to add another chapter — one where Cascadia becomes the world’s standard-bearer for innovation that uplifts both people and planet.”

The Cascadia Innovation Corridor, which Gregoire chairs, released the report this morning as it kicks off its two-day conference. The economic advocacy group’s eighth annual event is being held in Seattle.

The study is built on an analysis by the Boston Consulting Group that ranks Cascadia’s three metro areas against 15 comparable regions in the U.S. and Canada for their economic competitiveness, including livability, workforce, and business and innovation climate. Seattle came in fourth behind Boston, Austin and Raleigh, while Portland ranked 13th and Vancouver 14th.

Over the past decade, the region’s gross domestic product and populations have both grown significantly, and when combined, their economies approach the 18th largest in the world.

Cascadia’s strengths, the report explains, include tech engines such as cloud giants Microsoft and Amazon in Washington, silicon chip manufacturing in Oregon, and quantum innovation in Vancouver, as well as academic excellence from the University of Washington, University of British Columbia and Oregon State University.

But as time goes on and as business and civic leaders aim for the prize of AI dominance, cracks in the system are increasingly troubling.

• Business costs are rising and there are mounting regulatory concerns — but it’s a tricky picture. Seattle, for example, often turns to B&O and headcount taxes to cover costs, while the state struggles to balance budgets in the absence of an income tax.
• Housing affordability is continuing to decline for many residents in these metro areas.
• Skilled tech workers are leaving Portland, in particular, and Seattle relies heavily on foreign workers receiving H1-B visas, which are less certain under the Trump administration.
• The clean, affordable energy that was once abundant in the Pacific Northwest is decreasingly available as droughts reduce river flows that drive hydropower dams and electricity demand increases with rapid data center growth.

The report notes that multiple regions around the U.S. and Canada have created AI-focused hubs with hundreds of millions of dollars in public and private funding to bolster their hold on the sector.

New Jersey has a half-billion dollar “AI Moonshot” program including tax incentives and public-worker AI training programs; New York’s “Empire AI Consortium” has an AI computing training center at the University of Buffalo and startup supports; and California has a public-private task force to increase AI adoption within government services and connecting tech leaders with state agencies.

For its part, Seattle Mayor Bruce Harrell announced a “responsible AI plan” this fall that provides guidelines for the municipality’s use of artificial intelligence and its support of the AI tech sector as an economic driver, which includes the earlier launches of the startup-focused AI House and Foundations.

But what the region really needs to succeed is a collaborative effort tapping all of the metro areas’ assets.

“For Cascadia, the lesson is clear: without a coordinated strategy that links our strengths in cloud computing, semiconductors, and research, we risk falling behind,” states the Cascadia Innovation Corridor report. “Acting together, we can position Cascadia not just to keep pace, but to lead.”

Amazon confirmed Tuesday that it is cutting about 14,000 corporate jobs, citing a need to reduce bureaucracy and become more efficient in the new era of artificial intelligence.

In a message to employees, posted on the company’s website, Amazon human resources chief Beth Galetti signaled that the cutbacks are expected to continue into 2026, while indicating that the company will also continue to hire in key strategic areas.

Reuters reported Monday that the number of layoffs could ultimately total as many as 30,000 people, which is still a possibility as the cutbacks continue into next year. At that scale, the overall number of job cuts could eventually be the largest in Amazon’s history, exceeding the 27,000 positions that the company eliminated in 2023 across multiple rounds of layoffs.

“This generation of AI is the most transformative technology we’ve seen since the Internet, and it’s enabling companies to innovate much faster than ever before,” wrote Galetti, senior vice president of People Experience and Technology. Amazon needs “to be organized more leanly, with fewer layers and more ownership, to move as quickly as possible for our customers and business,” she explained.

Amazon’s corporate workforce numbered around 350,000 people in early 2023, the last time the company provided a public number. At that scale, the initial reduction of 14,000 represents about 4% of Amazon’s corporate workforce. However, the number is a much smaller fraction of its overall workforce of 1.55 million people, which includes workers in its warehouses.

Although the cuts are expected to be global, they are likely to hit especially hard in the Seattle region, home to the company’s first headquarters and its largest corporate workforce. The tech hub has already felt the impact of major layoffs by Microsoft and many other companies in recent months.

The cuts come two days before Amazon’s third quarter earnings report. Amazon and other cloud giants have been pouring billions into capital expenses to boost AI capacity. Cutting jobs is one way of showing operating-expense discipline to Wall Street.

In a memo to employees in June, Amazon CEO Andy Jassy wrote that he expected Amazon’s total corporate workforce to get smaller over time as a result of efficiency gains from AI. 

Jassy took over as Amazon CEO from founder Jeff Bezos in mid-2021. In recent years he has been pushing to reduce management layers and eliminate bureaucracy inside the company, saying he wants Amazon to operate like the “world’s largest startup.” 

Bloomberg News reported this week that Jassy has told colleagues that parts of the company remain “unwieldy” despite the 2023 layoffs and other efforts to streamline operations. 

Reuters cited sources saying the magnitude of the cuts is also a result of Amazon’s strict return-to-office policy failing to cause enough employees to quit voluntarily. Amazon brought workers back five days a week earlier this year.

Impacted teams and people will be notified of the layoffs today, Galetti wrote.

Amazon is offering most impacted employees 90 days to find a new role internally, though the timing may vary based on local laws, according to the message. Those who do not find a new position at Amazon or choose to leave will be offered severance pay, outplacement services, health insurance benefits, and other forms of support.

Meta plans to lay off more than 100 employees in Washington state as part of a broader round of cuts within its artificial intelligence division.

A new filing with the state’s Employment Security Department shows 101 employees impacted, including 48 in Bellevue, 23 in Seattle, and four in Redmond, along with 23 remote workers based in Washington.

The filing lists dozens of affected roles across Meta’s AI research and infrastructure units, including software engineers, AI researchers, and data scientists. Meta product managers, privacy specialists, and compliance analysts were also affected.

Meta is cutting around 600 positions in its AI unit, Axios reported last week. The company is investing heavily in AI and wants to create a “more agile operation,” according to an internal memo cited by Axios. Meta has just under 3,000 roles within its superintelligence lab, CNBC reported.

The separations at Meta in Washington take effect Dec. 22, according to the Worker Adjustment and Retraining Notification (WARN) notice filed Oct. 22.

Meta employs thousands of people across multiple offices in the Seattle region, one of its largest engineering hubs outside Menlo Park.

The latest reductions mark another contraction for Meta’s Pacific Northwest footprint following multiple rounds of layoffs over the past several years.

The company’s rapid expansion in Seattle over the past decade made it one of the emblems of the region’s tech boom, coinciding with Microsoft’s resurgence and Amazon’s rise.

Among the Bay Area titans, Google was among the first to establish a Seattle-area engineering office, way back in 2004. However, it was Facebook’s decision to open its own outpost across from Pike Place Market in 2010 that really got the attention of their Silicon Valley tech brethren.

In the decade that followed, out-of-town companies set up more than 130 engineering centers in the region.

However, more recently Meta has made moves to trim its Seattle-area footprint.

Apple earlier this year took over a building previously occupied by Meta in Seattle’s South Lake Union neighborhood, near Amazon’s headquarters. CoStar reported in April that Meta listed its other Arbor Blocks building for sublease.

Meta previously gobbled up much of the planned office space at the Spring District, a sprawling development northeast of downtown Bellevue, including a building that was originally going to be a new REI headquarters. But it has subleased some of the space since then to companies such as Snowflake, which recently took an entire building from Meta at the Spring District.

Meta’s office in Redmond, near Microsoft’s headquarters, is focused on its mixed reality development.

GeekWire has reached out to the company for an updated Seattle-area headcount.

Meta’s cuts come amid reported layoffs at Amazon that could impact up to 30,000 workers.

Tech companies have laid off more than 128,000 employees this year, according to Layoffs.fyi. Last year, companies cut nearly 153,000 positions.

Amazon is preparing to lay off as many as 30,000 corporate employees in a sweeping workforce reduction intended to reduce expenses and compensate for over-hiring during the pandemic, according to a report from Reuters on Monday.

GeekWire has contacted Amazon for comment.

Layoff notifications will start going out via email on Tuesday, according to Reuters, which cited people familiar with the matter. One employee at Amazon told GeekWire the workforce is on “pins and needles” in anticipation of cuts.

Bloomberg reported that cuts will impact several business units, including logistics, payments, video games, and Amazon Web Services.

Amazon’s corporate workforce numbered around 350,000 in early 2023. It has not provided an updated number since then.

The company’s last significant layoff occurred in 2023 when it cut 27,000 corporate workers in multiple stages. Since then the company has made a series of smaller layoffs across different business units.

Fortune reported this month that Amazon planned to cut up to 15% of its human resources staff as part of a wider layoff.

Amazon has taken a cautious hiring approach with its corporate workforce, following years of huge headcount growth. The company’s corporate headcount tripled between 2017 and 2022, according to The Information.

The reported cuts come as Amazon is investing heavily in artificial intelligence. The company said earlier this year it expects to increase capital expenditures to more than $100 billion in 2025, up from $83 billion in 2024, with a majority going toward building out capacity for AI in AWS.

Amazon CEO Andy Jassy also hinted at potential workforce impact from generative AI earlier this year in a memo to employees that was shared publicly.

“We will need fewer people doing some of the jobs that are being done today, and more people doing other types of jobs,” he wrote. “It’s hard to know exactly where this nets out over time, but in the next few years, we expect that this will reduce our total corporate workforce as we get efficiency gains from using AI extensively across the company.”

Amazon reported 1.54 million total employees as of June 30 — up 3% year-over-year. The majority of the company’s workforce is made up of warehouse workers.

Amazon employs roughly 50,000 corporate and tech workers in buildings across its Seattle headquarters, with another 12,000 in Bellevue.

The company reports its third quarter earnings on Thursday afternoon.

Fellow Seattle-area tech giant Microsoft has laid off more than 15,000 people since May as it too invests in AI and data center capacity. Microsoft has cut more than 3,200 roles in Washington this year.

Last week, The New York Times cited internal Amazon documents and interviews to report that the company plans to automate as much as 75% of its warehouse operations by 2033. According to the report, the robotics team expects automation to “flatten Amazon’s hiring curve over the next 10 years,” allowing it to avoid hiring more than 600,000 workers even as sales continue to grow.

GeekWire reporter Kurt Schlosser contributed to this story.

Zulily may no longer be a dominant player in Seattle’s tech scene, but physical pieces of the online retailer will live on in Evergreen Goodwill facilities across the region.

Hundreds of office chairs, desks, kitchen appliances, IT equipment, and more has been donated to Goodwill by Vanbarton Group, a commercial real estate investment firm that now owns the onetime Zulily building at 2601 Elliott Ave.

Vanbarton plans to convert the building, which occupies a full block near the waterfront, to 262 apartments, according to a Daily Journal of Commerce report from July.

A once-prominant online retailer, Zulily was a darling of Seattle’s growing tech scene when it was valued at $4 billion following its IPO in 2013. But after QVC parent Qurate paid $2.4 billion to buy the company in 2015, it was sold to Los Angeles investment firm Regent in May 2023 and eventually shut down.

In March, Zulily got a new owner for the third time in two years when Beyond, which emerged as a surprise buyer in 2024, announced plans to sell a majority stake in Zulily to Lyons Trading Company, the parent company of flash sales site Proozy.com.

Evergreen Goodwill said in a news release that the donation, facilitated by Vanbarton Group’s outreach, saved the nonprofit an estimated $100,000 in equipment costs and diverted valuable resources from landfills.

The office items are being repurposed in multiple locations, including Goodwill’s new Georgetown operations center, scheduled to open this fall, and job training and education centers that it operates in five counties.

Remaining items will be sold in Goodwill stores, with proceeds supporting free job training and education programs for people facing barriers to employment, according to Goodwill.

Previously:

• Zulily goes through another ownership change as Beyond to sell majority stake in retail site for $5M
• Zulily’s downfall: How the high-flying online retailer soared, sank, and shut down

Pioneer Square Labs has launched more than 40 tech startups and vetted 500-plus ideas since creating its studio a decade ago in Seattle.

Now it’s testing whether its company-building expertise and data on successful startup formulas can be codified into software — with help from the latest AI models.

PSL just unveiled Lev, a new project that aims to be an “AI co-founder” for early stage entrepreneurs.

Developed inside PSL and now rolling out publicly, Lev can evaluate ideas, score their potential, and help founders develop them into companies.

Lev grew out of an internal PSL tool that used PSL’s proprietary rubric to score startup ideas. The studio decided to turn it into a product after outside founders who tested early versions wanted access for themselves.

Here’s how it works:

• Users start by entering an idea (along with any associated information/background) and selecting “venture” or “bootstrap.”
• Lev walks founders through milestones from solution to customer discovery, go-to-market, and product build.
• It can generate “assets” like interview scripts, outreach templates, competitive maps, pricing models, brand palettes, customer personas, landing pages, potential leads, and even product specs.

“We’re mapping a lot of the PSL process into it,” said T.A. McCann, managing director at PSL.

Lev’s structured workflow sets it apart from generic chatbots, said Shilpa Kannan, principal at PSL.

“The sequencing of these components as you go through the process is one of the biggest value-adds,” she said.

Lev joins a growing number of startups leveraging AI to act as an idea validation tool for early-stage founders, though its precise approach makes it stand out.

Upcoming features will add team-building and fundraising modules and let users trigger actions — such as sending emails or buying domains — directly from within the platform.

McCann envisions Lev eventually connecting to tools like Notion and HubSpot to serve as a “command center” for running a company — integrating tools, drafting investor updates, tracking competitors, and suggesting priorities. There are several competitors in this space offering different versions of “AI chief of staff” products.

On a broader level, Lev raises an existential question for PSL: what happens when a startup studio teaches an AI to do the things that make a startup studio valuable?

“In some ways, this is ‘Innovators Dilemma,’ and you have to cannibalize yourself before someone else does it,” McCann said, referencing Clayton Christensen’s concept of technology disruption.

PSL also sees Lev as a potential funnel for entrepreneurs it could work with in the future. And it’s a way to expand the studio’s reach beyond its focus on the Pacific Northwest.

“It’s scaling our knowledge in a way that we wouldn’t be able to do otherwise,” McCann said.

Kannan and Kevin Leneway, principal at PSL, wrote a blog post describing how PSL designed the backbone of Lev and how the firm used it to generate its own high quality startup ideas at higher volumes with lower cost.

“As we see more and more individuals become founders with the support of AI, we are incredibly excited for the potential increase in velocity and successful outcomes from methodologies like ours that focus on upfront ideation and validation,” they wrote.

Kannan told GeekWire that PSL is prioritizing founders’ privacy and intellectual property. “We are making intentional product and technical decisions to ensure Lev is designed from the ground up to safeguard ideas and founder data, including guardrails on data we collect and our team can access,” she said.

For now, PSL is targeting venture-scale founders — people in tech companies or accelerators with ambitions to build fast-growing startups. But McCann believes Lev could eventually empower solo operators running multiple micro-businesses.

Lev is currently free for one idea, $20 per month for up to five ideas, and $100 per month for 10 ideas and advanced features. It’s available on a waitlist basis.

Lev also offers a couple fun tools to help boost its own marketing, including a founder “personality test” and an “idea matcher” that produces startup concepts based on your interests and experience.

— Deb Hall Lefevre, the longtime tech exec who was most recently CTO at Starbucks, announced her retirement on Sunday in a LinkedIn post.

Hall Lefevre resigned from Starbucks last month, according to a Sept. 26 report from Reuters, which cited a memo sent to staff about her departure.

The move came amid layoffs and various tech-related changes at the Seattle coffee giant.

“After an incredible journey leading technology and digital transformation across some of the world’s most iconic brands, including Starbucks, Circle K/Couche Tard and McDonald’s, it’s time to step into retirement,” Hall Lefevre said in her LinkedIn post.

“As I turn the page, I look forward to more time with family, continuing my tech and board work, and cheering on the next generation of leaders shaping the future,” she added.

Hall Lefevre, who was also an executive vice president, joined Starbucks in 2022. She previously spent more than 16 years at McDonald’s, where she was a corporate vice president and CIO, leading the fast food giant’s technology and digital commerce strategy. She was also EVP and CTO at Circle K Stores.

Ningyu Chen, who was senior vice president of global experience technology, is now interim chief technology officer at Starbucks.

Starbucks last month announced plans to lay off around 900 non-retail employees and close underperforming stores mainly in the U.S. and Canada. Starbucks previously cut 1,100 corporate workers in February.

Under the leadership of CEO Brian Niccol, the former Chipotle CEO who joined the company last year, Starbucks is making a bevy of technology tweaks as it tries to curb slumping sales.

— Lindo St. Angel, vice president of hardware for Amazon’s Lab126 devices group, is departing at the end of the month. Reuters first reported the news.

St. Angel joined Lab126 in 2010. The business unit, based in Silicon Valley, launched in 2004 and helped develop Amazon devices such as the Kindle Fire, Fire TV, Amazon Echo, and other hardware.

— Mark Jewett joined New York City health data company Komodo Health as chief marketing officer. Jewett was previously a senior vice president at Informatica and CMO at SmartRecruiters. He also was a SVP and co-interim CMO at Tableau, and spent 15 years at Microsoft in various leadership roles.

Founded in 2014, Komodo Health reached a $3.3 billion valuation in 2021. The company helps healthcare stakeholders integrate data and generate insights related to treatment, research, and more.

— Nancy Mounir joined Oracle Cloud Infrastructure as a vice president leading security programs and platforms.

Mounir previously spent more than 12 years at Microsoft, most recently as a senior director and chief of staff overseeing the company’s Secure Future Initiative.

In a LinkedIn post, Mounir said she is “looking forward to a great journey of learning, innovation and growth with the Security Platform team!”

She added: “Extremely grateful for my time at Microsoft and could not be more proud of what we accomplished together over the years!”

Mounir initially worked at Microsoft from 2012 to 2015 in supply chain, and left to spend a year at Amazon working on advertising and accounting teams. She returned to Microsoft in 2016.

— Priya Vaidyanathan took a new role at Microsoft as director of product and design for Microsoft’s AI skilling platform. Vaidyanathan returned to Microsoft in 2020 after two previous stints and was most recently a group product manager. She previously founded a mealkit startup called SnapCurry and was a senior technical product manager at Amazon.

“This next chapter is about helping people everywhere gain the skills and confidence to grow with AI, creating opportunity, resilience, and impact at every level,” she wrote on LinkedIn.

— Jim Chi was named executive director of Oregon Startup Center, which is going through a relaunch, according to Portland Business Journal. Chi is also president of Oregon Sports Angels and is a longtime product management leader.

SAN FRANCISCO — Putting on Amazon’s new smart delivery glasses felt surprisingly natural from the start. Despite their high-tech components and slightly bulky design, they were immediately comfortable and barely heavier than my normal glasses.

Then a few lines of monochrome green text and a square target popped up in the right-hand lens — reminding me that these were not my regular frames. 

Occupying just a portion of my total field of view, the text showed an address and a sorting code: “YLO 339.” As I learned, “YLO” represented the yellow tote bag where the package would normally be found, and “339” was a special code on the package label.

My task: find the package with that code. Or more precisely, let the glasses find them.

As soon as I looked at the correct package label, the glasses recognized the code and scanned the label automatically. A checkmark appeared on a list of packages in the glasses.

Then an audio alert played from the glasses: “Dog on property.”

When all the packages were scanned, the tiny green display immediately switched to wayfinding mode. A simple map appeared, showing my location as a dot, and the delivery destination marked with pins. In this simulation, there were two pins, indicating two stops. 

After putting the package on the doorstep, it was time for proof of delivery. Instead of reaching for a phone, I looked at the package on the doorstep and pressed a button once on the small controller unit —the “compute puck” — on my harness. The glasses captured a photo.

With that, my simulated delivery was done, without ever touching a handheld device.

In my very limited experience, the biggest concern I had was the potential to be distracted — focusing my attention on the text in front of my eyes rather than the world around me. I understand now why the display automatically turns off when a van is in motion. 

But when I mentioned that concern to the Amazon leaders guiding me through the demo, they pointed out that the alternative is looking down at a device. With the glasses, your gaze is up and largely unobstructed, theoretically making it much easier to notice possible hazards. 

Beyond the fact that they’re not intended for public release, that simplicity is a key difference between Amazon’s utilitarian design and other augmented reality devices — such as Meta Ray-Bans, Apple Vision Pro, and Magic Leap — which aim to more fully enhance or overlay the user’s environment.

One driver’s experience

KC Pangan, who delivers Amazon packages in San Francisco and was featured in Amazon’s demo video, said wearing the glasses has become so natural that he barely notices them. 

Pangan has been part of an Amazon study for the past two months. On the rare occasions when he switches back to the old handheld device, he finds himself thinking, “Oh, this thing again.”

“The best thing about them is being hands-free,” Pangan said in a conversation on the sidelines of the Amazon Delivering the Future event, where the glasses were unveiled last week.

Without needing to look down at a handheld device, he can keep his eyes up and stay alert for potential hazards. With another hand free, he can maintain the all-important three points of contact when climbing in or out of a vehicle, and more easily carry packages and open gates.

The glasses, he said, “do practically everything for me” — taking photos, helping him know where to walk, and showing his location relative to his van. 

While Amazon emphasizes safety and driver experience as the primary goals, early tests hint at efficiency gains, as well. In initial tests, Amazon has seen up to 30 minutes of time savings per shift, although execs cautioned that the results are preliminary and could change with wider testing.

Regulators, legislators and employees have raised red flags over new technology pushing Amazon fulfillment and delivery workers to the limits of human capacity and safety. Amazon disputes this premise, and calls the new glasses part of a larger effort to use technology to improve safety.

Using the glasses will be fully optional for both its Delivery Service Partners (DSPs) and their drivers, even when they’re fully rolled out, according to the company. The system also includes privacy features, such as a hardware button that allows drivers to turn off all sensors.

For those who use them, the company says it plans to provide the devices at no cost. 

Despite the way it may look to the public, Amazon doesn’t directly employ the drivers who deliver its packages in Amazon-branded vans and uniforms. Instead, it contracts with DSPs, ostensibly independent companies that hire drivers and manage package deliveries from inside Amazon facilities. 

This arrangement has periodically sparked friction, and even lawsuits, as questions have come up over DSP autonomy and accountability.

With the introduction of smart glasses and other tech initiatives, including a soon-to-be-expanded training program, Amazon is deepening its involvement with DSPs and their drivers — potentially raising more questions about who truly controls the delivery workforce.

From ‘moonshot’ to reality

The smart glasses, still in their prototype phase, trace their origins to a brainstorming session about five years ago, said Beryl Tomay, Amazon’s vice president of transportation.

Each year, the team brainstorms big ideas for the company’s delivery system. During one of those sessions, a question emerged: What if drivers didn’t have to interact with any technology at all?  

“The moonshot idea we came up with was, what if there was no technology that the driver had to interact with — and they could just follow the physical process of delivering a package from the van to the doorstep?” Tomay said in an interview. “How do we make that happen so they don’t have to use a phone or any kind of tech that they have to fiddle with?”

That question led the team to experiment with different approaches before settling on glasses. It seemed kind of crazy at first, Tomay said, but they soon realized the potential to improve safety and the driver experience. Early trials with delivery drivers confirmed the theory.

“The hands-free aspect of it was just kind of magical,” she said, summing up the reaction from early users.

The project has already been tested with hundreds of delivery drivers across more than a dozen DSPs. Amazon plans to expand those trials in the coming months, with a larger test scheduled for November. The goal is to collect more feedback before deciding when the technology will be ready for wider deployment.

Typically, Amazon would have kept a new hardware project secret until later in its development. But Reuters reported on the existence of the project nearly a year ago. (The glasses were reportedly code-named “Amelia,” but they were announced without a name.) And this way, Amazon can get more delivery partners involved, get input, and make improvements.

Future versions may also expand the system’s capabilities, using sensors and data to automatically recognize potential hazards such as uneven walkways.

How the technology works

Amazon’s smart glasses are part of a system that also includes a small wearable computer and a battery, integrated with Amazon’s delivery software and vehicle systems.

The lenses are photochromatic, darkening automatically in bright sunlight, and can be fitted with prescription inserts. Two cameras — one centered, one on the left — support functions such as package scanning and photo capture for proof of delivery. 

A built-in flashlight switches on automatically in dim conditions, while onboard sensors help the system orient to the driver’s movement and surroundings.

The glasses connect by a magnetic wire to a small controller unit, or “compute puck,” worn on the chest of a heat-resistant harness. The controller houses the device’s AI models, manages the visual display, and handles functions such as taking a delivery photo. It also includes a dedicated emergency button that connects drivers directly to Amazon’s emergency support systems.

On the opposite side of the chest, a swappable battery keeps the system balanced and running for a full route. Both components are designed for all-day comfort — the result, Tomay said, of extensive testing with drivers to ensure that wearing the gear feels natural when they’re moving around.

Connectivity runs through the driver’s official Amazon delivery phone via Bluetooth, and through the vehicle itself using a platform called “Fleet Edge” — a network of sensors and onboard computing modules that link the van’s status to the glasses. 

This connection allows the glasses to know precisely when to activate, when to shut down, and when to sync data. When a van is put in park, the display automatically activates, showing details such as addresses, navigation cues, and package information. When the vehicle starts moving again, the display turns off — a deliberate safety measure so drivers never see visual data while driving.

Data gathered by the glasses plays a role in Amazon’s broader mapping efforts. Imagery and sensor data feed into “Project Wellspring,” a system that uses AI to better model the physical world. This helps Amazon refine maps, identify the safest parking spots, pinpoint building entrances, and optimize walking routes for future deliveries.

Amazon says the data collection is done with privacy in mind. In addition to the driver-controlled sensor shut-off button, any imagery collected is processed to “blur or remove personally identifiable information” such as faces and license plates before being stored or used.

The implications go beyond routing and navigation. Conceivably, the same data could also lay the groundwork for greater automation in Amazon’s delivery network over time.

Testing the delivery training

In addition to trying the glasses during the event at Amazon’s Delivery Station in Milpitas, Calif., I experienced firsthand just how difficult the job of delivering packages can be. 

• Strapped into a harness for a slip-and-fall demo, I learned how easily a driver can lose footing on slick surfaces if not careful to walk properly. 
• I tried a VR training device that highlighted hidden hazards like pets sleeping under tires and taught me how to navigate complex intersections safely.
• My turn in the company’s Rivian van simulator proved humbling. Despite my best efforts, I ran red lights and managed to crash onto virtual sidewalks.

The simulator, known as the Enhanced Vehicle Operation Learning Virtual Experience (EVOLVE), has been launched at Amazon facilities in Colorado, Maryland, and Florida, and Amazon says it will be available at 40 sites by the end of 2026. 

It’s part of what’s known as the Integrated Last Mile Driver Academy (iLMDA), a program available at 65 sites currently, which Amazon says it plans to expand to more than 95 delivery stations across North America by the end of 2026.

“Drivers are autonomous on the road, and the amount of variables that they interact with on a given day are countless,” said Anthony Mason, Amazon’s director of delivery training and programs, who walked me through the training demos. One goal of the training, he said, is to give drivers a toolkit to pull from when they face challenging situations.

Suffice it to say, this is not the job for me. But if Amazon’s smart glasses live up to the company’s expectations, they might be a step forward for the drivers doing the real work.

Get caught up on the latest technology and startup news from the past week. Here are the most popular stories on GeekWire for the week of Oct. 19, 2025.

Sign up to receive these updates every Sunday in your inbox by subscribing to our GeekWire Weekly email newsletter.

Most popular stories on GeekWire

AWS outage was not due to a cyberattack — but shows potential for ‘far worse’ damage

The outage serves as warning sign for a potentially more disruptive situation and reflects “tech monoculture” in a global infrastructure. … Read More

How the AWS outage happened: Amazon blames rare software bug and ‘faulty automation’ for massive glitch

A detailed explanation of this week’s Amazon Web Services outage, released Thursday morning, confirms that it wasn’t a hardware glitch or an outside attack but a complex, cascading failure triggered by a rare software bug in one of the company’s most critical systems. … Read More

Seattle mayor says Microsoft and Amazon have a ‘moral obligation’ to give back to the city

Harrell’s comments reflect a delicate balance faced by city leaders — ensuring that Seattle’s global tech corporations continue to bolster the economy and tax base, while addressing the ripple effects on housing, transportation, and communities. … Read More

Amazon customers report delivery delays after major AWS outage

Amazon’s e-commerce customers are experiencing unusual delivery delays following the Amazon Web Services outage on Monday — suggesting that the cloud glitch has impacted the company’s own operations more than than previously reported. … Read More

Tim Chen was deemed ‘too nerdy’ for venture capital. Now he runs one of the hottest startup funds in tech.

When Tim Chen tried to break into venture capital six years ago, multiple firms in Seattle turned him down. … Read More

Alaska Airlines cancels 360 flights, says significant IT outage was due to ‘failure’ at a data center

The impact of the outage was evident at Sea-Tac Airport on Thursday evening, where long lines wrapped around the concourse and a maze of suitcases piled up in the baggage claim area. … Read More

AWS outage hits major apps and services, resurfacing old questions about cloud redundancy

Amazon Web Services is recovering after an outage that disrupted Facebook, Snapchat, Fortnite, Coinbase and other major platforms, once again illustrating the internet’s heavy reliance on the cloud giant and a lack of redundancy in online services. … Read More

Amazon unveils AI-powered augmented reality glasses for delivery drivers

Amazon says it’s working on AI-powered augmented reality glasses for delivery drivers, offering hands-free navigation, package scanning, and proof-of-delivery tools. … Read More

Satya Nadella’s pay tops $96M as Microsoft stock soars; Walmart CFO set to join board

Microsoft CEO Satya Nadella’s total compensation rose nearly 22% to $96.5 million, driven largely by the company’s surging stock price, a new filing reveals. … Read More

Carbon Robotics raises $20M as LaserWeeder maker plans secretive new ‘AI robot’ for farms

“It’ll blow your mind,” founder and CEO Paul Mikesell said of a carbon Robotics machine that relies on the same AI system used in Carbon’s other equipment. … Read More

When I was a kid, my mom used to call my Nintendo the “anti-social idiot box.” The widespread assumption back then was that video games, in any format, were a new and particularly efficient way to waste time and money while also becoming an obsessed shut-in.

Over the course of the subsequent decades, video games have grown into both a multi-billion-dollar industry and a much more socially acceptable hobby. While gaming does attract its share of anti-social obsessives, just like any other form of media, I’ve found it’s much more common for people to meet and bond over their mutual enjoyment of the hobby.

Whether it’s friends you meet through MMORPGs or fighting games, finding stories and characters that deeply resonate with you, or discussing your latest game in a shared space like Bluesky or a message board, video games often have a positive impact on the people who play them. That impact simply doesn’t get a fraction of the press of gaming’s various downsides.

That ability is the focus of a new paper from the University of Washington, “’I Would Not Be This Version of Myself Today’: Elaborating on the Effects of Eudaimonic Gaming Experiences.” The paper, by Nisha Devasia, Georgia Kenderova, Julie A. Kientz, Jin Ha Lee, and Michele Newman, was the focus of a presentation this month at the Annual Symposium on Computer-Human Interaction in Play (CHI-PLAY) in Pittsburgh.

For the paper, the authors surveyed 166 respondents about the “meaningful experiences” they’d had as a result of playing video games, such as rich storytelling, becoming interested in specific skill development, or the experience of watching a narrative shift based upon the player’s in-game actions.

According to the paper’s abstract, “While much of the research in digital games has emphasized hedonic experiences, such as flow, enjoyment, and positive affect, recent years have seen increased interest in eudaimonic gaming experiences, typically mixed-affect and associated with personal meaningfulness and growth.”

Of the 166 respondents, 78% reported that they’d had meaningful, life-changing experiences from their time playing video games, the researchers said in a UW News story about the paper.

“We highlighted three conclusions drawn from modeling the data,” Devasia told UW News. “The first is that playing games during stressful times was strongly correlated with positive outcomes for physical and mental health. For example, during COVID, people played games they felt strongly improved their mental health, such as Stardew Valley.”

Devasia also noted that other respondents had developed new interests, such as sports, due to video games they’d played, or gained insight into themselves or their identities from the journeys undertaken by video game protagonists.

“Playing as a character and seeing your choices change the course of events is pretty unique to games, compared with other narrative media like novels or movies,” Devasia said.

“As researchers, we develop games for learning, for instance, for teaching people about misinformation or AI, or promote digital civic engagement, because we want to foster meaningful experiences,” Lee added. “But a lot of the existing research just focuses on the short-term effects of games. This study really helps us understand what actually caused a game to make a difference in someone’s life.”

It sounds obvious at first glance if you’re someone who grew up around video games. It’s almost a given that there’s at least one game that made a serious mark on you somehow, especially if you live in a heavily nerd-coded space like the greater Seattle area.

Anecdotally, that strikes me as an underexplored part of the hobby. If anything, there’s a strange critical drive in the space to deliberately treat gaming as disposable pop culture, without any real meaning or lasting value. If you read any op-ed in the gaming press that discusses the cultural or political meaning of a video game, someone will inevitably show up in the comments to accuse the author of overthinking something that isn’t meant to matter. It’s “just a game.”

Even so, modern video games have just as much ability to resonate with their audience as any novel or film, and people who’ve grown up with them will take lessons away from that. It’s something we don’t discuss often enough in the field; we’ll talk at length about how video games are fun or socially acceptable now or a surprisingly big business, but their influence as culture is less discussed.

“People have a tendency to treat technology as a monolith, as if video games are either good or bad, but there’s so much more nuance,” Kientz told UW News. “The design matters. This study hopefully helps us untangle the positive elements. Certainly, there are bad elements — toxicity and addictiveness, for example. But we also see opportunities for growth and connection.”

From empty offices in 2020 to AI colleagues in 2025, the way we work has been completely rewired over the past five years. Our guest on this week’s GeekWire Podcast studies these changes closely along with her colleagues at Microsoft.

Colette Stallbaumer is the co-founder of Microsoft WorkLab, general manager of Microsoft 365 Copilot, and the author of the new book, WorkLab: Five years that shook the business world and sparked an AI-first future, from Microsoft’s 8080 Books.

As Stallbaumer explains in the book, the five-year period starting with the pandemic and continuing to the current era of AI represents one continuous transformation in the way we work, and it’s not over yet.

“Change is the only constant—shifting norms that once took decades to unfold now materialize in months or weeks,” she writes. “As we look to the next five years, it’s nearly impossible to imagine how much more work will change.”

Listen below for our conversation, recorded on Microsoft’s Redmond campus. Subscribe on Apple or Spotify, and continue reading for key insights from the conversation.

The ‘Hollywood model’ of teams: “What we’re seeing is this movement in teams, where we’ll stand up a small squad of people who bring their own domain expertise, but also have AI added into the mix. They come together just like you would to produce a film. A group of people comes together to produce a blockbuster, and then you disperse and go back to your day job.”

The concept of the ‘frontier firm’: “They’re not adding AI as an ingredient. AI is the business model. It’s the core. And these frontier firms can have a small number of people using AI in this way, generating a pretty high run rate. So it’s a whole new way to think about shipping, creating, and innovating.”

The fallacy of ‘AI strategy’: “The idea that you just need to have an ‘AI strategy’ is a bit of a fallacy. Really, you kind of want to start with the business problem and then apply AI. … Where are you spending the most and where do you have the biggest challenges? Those are great areas to actually think about putting AI to work for you.”

Adapting to AI: “You have to build the habit and build the muscle to work in this new way and have that moment of, ‘Oh, wait, I don’t actually need to do this.’ “

The biggest risk related to AI: “The biggest risk is not AI in and of itself. It’s that people won’t evolve fast enough with AI. It’s the human risk and ability to actually start to really use these new tools and build the habit.”

Human creativity and AI: “It still takes that spark and that seed of creativity. And then when you combine it with these new tools, that’s where I have a lot of hope and optimism for what people are going to be able to do and invent in the future.”

Audio editing by Curt Milton.

Subscribe to GeekWire in Apple Podcasts, Spotify, or wherever you listen.

“It is here, it is real, it is happening,” said play-by-play announcer Ian Eagle. “The NBA on Prime.”

And with that, Amazon’s foray into live streaming NBA games tipped off.

Amazon marked a major milestone with its growing sports portfolio on Friday, broadcasting its first-ever live NBA game around the world. The matchup — Celtics vs. Knicks — was part of an 11-year deal that gives Amazon exclusive rights to select regular season and playoff games.

We watched the game via Prime Video — accessible with a $139/year Prime subscription — and came away impressed.

The stream ran seamlessly across Fire TV, iPhone, and MacBook. The quality was crisp, load times near-instant, and there wasn’t a hint of lag — at least on a home WiFi connection. Amazon’s 1080p HDR video and 5.1 surround sound were a slam dunk.

The broadcast looked and felt like a traditional national telecast. The graphics mirrored what fans expect from ESPN or TNT, the commentary came from familiar voices — Eagle and Stan Van Gundy — and the pregame show from featured a slick set with former NBA stars at Amazon MGM Studios.

But under the surface, Amazon quietly tested a new frontier: in-stream sports betting.

The most noticeable new feature was the FanDuel integration, Amazon’s latest experiment in blending live sports and interactive technology.

Fans watching on Fire TV could log into their FanDuel accounts through Prime Video to view real-time betting information and track wagers directly within the broadcast.

You can’t make actual bets on Prime Video — not yet, at least— but it marks a subtle yet significant shift in how live sports may evolve on streaming platforms.

And it comes at a fascinating moment: the NBA is dealing with a major betting scandal that made headlines this week and involves the FBI.

I was surprised when NBA Commissioner Adam Silver joined the broadcast for a live interview. Sideline reporter Cassidy Hubbarth opened by asking about the scandal.

Silver said he was “deeply disturbed” upon hearing the news.

“There’s nothing more important to the league and its fans than the integrity of the competition,” he said.

Silver also praised Amazon’s coverage: “I should have started [by saying] how excited we are to be on Amazon,” he said. “I guess I wouldn’t have predicted that my first interview on Amazon would be about sports betting.”

The interview underscored how Amazon’s coverage didn’t shy away from real-time news relevance — adding a traditional journalistic layer within a tech-powered broadcast.

It was also a surreal moment: the NBA’s top official discussing a sports betting scandal during the league’s debut on a platform now integrating betting tools into its stream.

Amazon has other new tech-fueled features including advanced NBA stats powered by Amazon Web Services — but I didn’t notice that during Friday’s broadcast.

One of the only stumbles for me came on the Fire TV user experience, which feels clunky compared to mobile or desktop. Navigation wasn’t intuitive, and the remote’s button mapping made simple actions harder than expected.

But overall, the whole experience felt less like a tech demo and more like a finished product.

Amazon’s sports strategy is crystalizing: use live sports to drive Prime signups and boost engagement across its ecosystem. The broadcast was promoted on Amazon’s homepage and apps. Live sports also helps fuel Amazon’s growing advertising business.

Bloomberg reported that Amazon is paying $1.8 billion annually for the NBA rights.

As more people cut the cord, sports leagues are increasingly partnering with tech companies as their existing deals with traditional cable providers expire. Companies like Amazon, Apple, and Netflix are hungry for valuable content such as live sports to draw more subscribers to their respective platforms.

Amazon also aired the Timberwolves vs. Lakers game on Friday evening. It will stream 66 regular season games this year, along with some playoff games.

The company also separate deals to air the NFL’s Thursday Night Football, WNBA, and Premier League, among other sports-related programming on its Prime Video platform.

The NBA debut on Friday was a reminder of Amazon’s approach to live sports: combine the reliability of broadcast TV with subtle tech layers — such as betting, data, and e-commerce — built on its AWS cloud infrastructure and Prime membership model.

The prime crew nails it again 👏

More of this and fewer hot takes! https://t.co/G3IN2BOyFO pic.twitter.com/swHUtlVXXN

— Oh No He Didn't (@ohnohedidnt24) October 25, 2025

Alaska Airlines already tried to shore up its IT infrastructure after an outage in July forced the Seattle-based company to ground flights across the country.

Apparently, it wasn’t enough.

Alaska was hit with another major outage on Thursday, leading to a ground stop that lasted eight hours and resulted in more than 400 flights canceled across Alaska Airlines and its subsidiary Horizon Air.

In a new update Friday afternoon, the company said more than 49,000 passengers had their travel plans disrupted.

The outage was severe enough to postpone the company’s scheduled quarterly earnings call Friday. Shares were down more than 6%.

Alaska said it was still working to normalize operations.

The company has blamed the outage on a failure at its primary data center. It was not due to a cybersecurity incident.

“Following a similar disruption earlier this year, we took action to harden our systems, but this failure underscores the work that remains to be done to ensure system stability,” the company said in its latest update. “We are immediately bringing in outside technical experts to diagnose our entire IT infrastructure to ensure we are as resilient as we need to be. ”

It added: “The reliability of our technology is fundamental to our ability to serve guests and get them to where they need to be.”

Alaska said its July outage was caused by a failure of a “critical piece of hardware” at its data centers.

The airline operates a hybrid infrastructure, blending its own data centers with third-party cloud platforms, according to an interview last year with Vikram Baskaran, Alaska’s vice president of IT.

Alaska began migrating workloads to Microsoft Azure around 2015 and continues to maintain its own data centers for critical workloads, according to the interview.

The company last year partnered with Google Cloud on a generative AI-powered search experience.

The impact of this week’s outage was evident at Sea-Tac Airport on Thursday evening, where long lines wrapped around the concourse and a maze of suitcases piled up in the baggage claim area.

Alaska said Friday it does not have an estimate of the financial impact of the outage. The company’s Hawaiian Airlines subsidiary was not affected.

Alaska said the July outage was expected to reduce earnings by about $0.10 per share, or roughly $12 million.

The company on Thursday reported third quarter revenue of $3.8 billion, up 1.4% year-over-year, while profit dropped 69% to $123 million.

Hundreds of global leaders gathered in the Pacific Northwest this week for the inaugural One Ocean Week Seattle, a maritime conference with dozens of events that brought together company executives, government officials and advocates charting paths toward cleaner shipping, sustainable fishing and ocean conservation.

The conference, organized by Washington Maritime Blue, was anchored by Wednesday’s One Ocean Summit, where leaders from global companies with Seattle ties discussed their climate progress and the challenges of deploying sustainable technologies.

Seattle-based SSA Marine, a global marine terminal operator, has 200 locations worldwide, moving cargo from ships to terminals and onto trains and trucks. The company has carbon emissions targets and is working to shift from gas and diesel to electrical power for the machines moving moving the cargo, but the move requires juggling sometimes competing factors.

“If you have a piece of electrical equipment, you have to think about charging time that’s required in between shifts, and when can you actually fit it in there?” said Meghan Weinman, SSA Marine’s vice president of sustainability. “One of those big pieces of innovation that we really have to think about is the overlay of technology, labor planning, and can it do the job that we need it to do.”

Corvus Energy is a Norwegian clean shipping company with Seattle offices and a manufacturing facility in Bellingham, Wash. The business is helping vessels go electric with its maritime battery technologies, serving ferries, cruise ships, tugs, cranes and fishing boats.

It’s an evolving sector and the company spends up to 15% of its annual revenue on research and development to fine-tune its technology to meet demanding oceanic conditions.

“It is totally different to operate a battery in an EV versus a maritime setting,” said Corvus CEO Fredrik Witte. “For an EV, you’re traveling three, four hours a day, maybe. But in a maritime setting, you’re potentially operating 24/7.”

Seattle’s Trident Seafoods operates fishing boats and onshore production facilities, including the largest seafood processing plant in North America in Akutan, Alaska. While seafood typically has a much lower carbon footprint than beef, pork or dairy, the company wants to reduce the climate impacts associated with its operations.

But Paul Doremus, Trident Seafoods’ vice president of policy and sustainability, pointed to a hard reality: the company competes directly with Russian and Chinese seafood companies that are doing business under less stringent environmental regulations.

He said the seafood sector — “which has been kind of famously fragmented, small, fairly scrappy” — needs to come together to collectively make improvements.

Doremus applauded events like One Ocean Week Seattle for gathering maritime interests to draw attention and capital toward “sustainable use of the ocean for the benefit of local communities, regional and national.”

“I think that’s the next wave,” he said.

Collaboration and innovation

The call for collaboration echoed throughout the One Ocean Summit, which also featured former NOAA Administrator Jane Lubchenco, United Nations officials, and Norway’s ambassador to the U.S.

Washington Lt. Gov. Denny Heck gave a welcome address, highlighting the state’s maritime economy while calling out threats from plastic pollution, undersea noise, and environmental degradation.

“To face these challenges, we will need to develop new technologies and strengthen our institutions,” Heck said. “It will require sustainable fuel storage, habitat restoration, quiet propulsion and so many other inventions and innovations. But more importantly, it will require the dedication and teamwork of thousands of people.”

The message was reinforced by Haakon Vatle, leader of the One Ocean Expedition, which is sailing a 111-year-old Norwegian tall ship across the globe. The ship, named the Statsraad Lehmkuhl, was moored just outside Bell Harbor International Conference Center during the event.

“The role of our ship is to create attention and share knowledge of the crucial role of the ocean for a sustainable future,” Vatle said. “We’re going to use a ship to reduce the gap between science and the public — get the people we need for the ocean we want. We cannot save the ocean alone.”

Editor’s note: GeekWire reporter Lisa Stiffler was the volunteer emcee of the One Ocean Summit.

Out of Office is a new GeekWire series spotlighting the passions and hobbies that members of the Seattle-area tech community pursue outside of work.

• Name: Maksim Surguy.

• Day job: Senior design technologist for Amazon Devices, working on concepts for new devices or new features on existing devices, such as Fire TV, Alexa, and Echo smart speakers.

• Out-of-office passion: Using machines to create art.

Before he pursued a bachelor’s degree in computer science, Maksim Surguy made an initial — and brief — run at a bachelor’s in art.

“Two weeks later, I realized that I suck at art and I switched to computer science,” he laughed.

Fourteen years after completing his education at California State University, Fullerton, Surguy has found happiness and success in marrying the two disciplines, as a technologist and an artist in Seattle.

“My sketching is not to the level that I want, so instead I use code to create artwork,” he said in describing the “robot art” that occupies his free time.

Surguy not only relies on machines to generate his artwork, he creates the software tools that facilitate such art, whether the finished pieces exist as digital NFTs or as physical works such as pen plotter drawings made via scalable vector graphics.

“I spend a lot more time making the tools than actually using them,” Surguy said. “But other people use them to actually make something. So I enjoy both sides of this.”

Surguy is a 2018 graduate of the University of Washington’s Master of Science in Technology Innovation (MSTI), a program at the UW’s Global Innovation Exchange (GIX) — a joint initiative of the College of Engineering and Foster School of Business.

For a hardware/software project, he created a 3D-printed drawing machine with his own electronics program. During the process, he couldn’t find a community for like-minded people who make such things. So he started DrawingBots, a website/Discord that’s attracted thousands of artists and engineers.

Surguy was born and raised in Ukraine and was an accomplished breakdancer who competed as a professional in Eastern Europe when he was younger. He moved to the U.S. in 2004.

He’s been at Amazon for six years and his artwork has been displayed in the company’s headquarters buildings, in public exhibitions — including at Seattle’s NFT Museum, and on his website and social media channels. He’s also written extensively about technology.

And in the blurring space between human and AI-created artwork, he’s leaning further into technology.

“I use AI for a lot of things, and especially now with code, it makes it easier to create tools that are custom and specific for whatever use case,” Surguy said. “I just open-sourced one last weekend. It’s a tool that allows artists to preview their artwork, how it’s going to look before they make it on paper. So it saves them time and money and art supplies.”

Most rewarding aspect of this pursuit: Surguy most enjoys the growing community he helped foster around the tools and art he makes.

“I got to know thousands of people that do this kind of stuff and are very interesting people,” he said. “Some of them were TED speakers. Some of them are PhDs, very well known researchers, scientists, artists. I had conversations with all of these people and consider some of them my friends. So that’s the most rewarding part.”

The lessons he brings back to work: “This kind of procedural and algorithmic art definitely has a place in making products that are digital experiences,” Surguy said of the connection between his hobby and his work at Amazon.

For example, his Devices team launched a dynamic art feature for Fire TV: a screen saver that created artwork on the fly based on data such as weather, time of day, and other inputs.

Surguy said the ideas he generates outside of work serve as inspiration for what he creates at work, whether it’s creative coding or simply expanding the boundaries of what he makes and how he makes it.

Read more Out of Office profiles.

Do you have an out-of-office hobby or interesting side hustle that you’re passionate about that would make for a fun profile on GeekWire? Drop us a line: tips@geekwire.com.

SAN FRANCISCO — Amazon showed off its latest robotics and AI systems this week, presenting a vision of automation that it says will make warehouse and delivery work safer and smarter. 

But the tech giant and some of the media at its Delivering the Future event were on different planets when it came to big questions about robots, jobs, and the future of human work. 

The backdrop: On Tuesday, a day before the event, The New York Times cited internal Amazon documents and interviews to report that the company plans to automate as much as 75% of its operations by 2033. According to the report, the robotics team expects automation to “flatten Amazon’s hiring curve over the next 10 years,” allowing it to avoid hiring more than 600,000 workers even as sales continue to grow.

In a statement cited in the article, Amazon said the documents were incomplete and did not represent the company’s overall hiring strategy.

On stage at the event, Tye Brady, chief technologist for Amazon Robotics, introduced the company’s newest systems — Blue Jay, a setup that coordinates multiple robotic arms to pick, stow, and consolidate items; and Project Eluna, an agentic AI model that acts as a digital assistant for operations teams.

Later, he addressed the reporters in the room: “When you write about Blue Jay or you write about Project Eluna … I hope you remember that the real headline is not about robots. The real headline is about people, and the future of work we’re building together.”

He said the benefits for employees are clear: Blue Jay handles repetitive lifting, while Project Eluna helps identify safety issues before they happen. By automating routine tasks, he said, AI frees employees to focus on higher-value work, supported by Amazon training programs.

Brady coupled that message with a reminder that no company has created more U.S. jobs over the past decade than Amazon, noting its plan to hire 250,000 seasonal workers this year. 

His message to the company’s front-line employees: “These systems are not experiments. They’re real tools built for you, to make your job safer, smarter, and more rewarding.”

‘Menial, mundane, and repetitive’

Later, during a press conference, a reporter cited the New York Times report, asking Brady if he believes Amazon’s workforce could shrink on the scale the paper described based on the internal report.

Brady didn’t answer the question directly, but described the premise as speculation, saying it’s impossible to predict what will happen a decade from now. He pointed instead to the past 10 years of Amazon’s robotics investments, saying the company has created hundreds of thousands of new jobs — including entirely new job types — while also improving safety.

He said Amazon’s focus is on augmenting workers, not replacing them, by designing machines that make jobs easier and safer. The company, he added, will continue using collaborative robotics to help achieve its broader mission of offering customers the widest selection at the lowest cost.

In an interview with GeekWire after the press conference, Brady said he sees the role of robotics as removing the “menial, mundane, and repetitive” tasks from warehouse jobs while amplifying what humans do best — reasoning, judgment, and common sense. 

“Real leaders,” he added, “will lead with hope — hope that technology will do good for people.”

When asked whether the company’s goal was a “lights-out” warehouse with no people at all, Brady dismissed the idea. “There’s no such thing as 100 percent automation,” he said. “That doesn’t exist.” 

Instead, he emphasized designing machines with real utility — ones that improve safety, increase efficiency, and create new types of technical jobs in the process.

When pressed on whether Amazon is replacing human hands with robotic ones, Brady pushed back: “People are much more than hands,” he said. “You perceive the environment. You understand the environment. You know when to put things together. Like, people got it going on. It’s not replacing a hand. That’s not the right way to think of it. It’s augmenting the human brain.”

Brady pointed to Amazon’s new Shreveport, La., fulfillment center as an example, saying the highly automated facility processes orders faster than previous generations while also adding about 2,500 new roles that didn’t exist before.

“That’s not a net job killer,” he said. “It’s creating more job efficiency — and more jobs in different pockets.”

The New York Times report offered a different view of Shreveport’s impact on employment. Describing it as Amazon’s “most advanced warehouse” and a “template for future robotic fulfillment centers,” the article said the facility uses about 1,000 robots. 

Citing internal documents, the Times reported that automation allowed Amazon to employ about 25% fewer workers last year than it would have without the new systems. As more robots are added next year, it added, the company expects the site to need roughly half as many workers as it would for similar volumes of items under previous methods.

Wall Street sees big savings

Analysts, meanwhile, are taking the potential impact seriously. A Morgan Stanley research note published Wednesday — the same day as Amazon’s event and in direct response to the Times report — said the newspaper’s projections align with the investment bank’s baseline analysis.

Rather than dismissing the report as speculative, Morgan Stanley’s Brian Nowak treated the article’s data points as credible. The analysts wrote that Amazon’s reported plan to build around 40 next-generation robotic warehouses by 2027 was “in line with our estimated slope of robotics warehouse deployment.”

More notably, Morgan Stanley put a multi-billion-dollar price tag on the efficiency gains. Its previous models estimated the rollout could generate $2 billion to $4 billion in annual savings by 2027. But using the Times’ figure — that Amazon expects to “avoid hiring 160,000+ U.S. warehouse employees by ’27” — the analysts recalculated that the savings could reach as much as $10 billion per year.

Back at the event, the specific language used by Amazon executives aligned closely with details in the Times report about the company’s internal communications strategy.

According to the Times, internal documents advised employees to avoid terms such as “automation” and “A.I.” and instead use collaborative language like “advanced technology” and “cobots” — short for collaborative robots — as part of a broader effort to “control the narrative” around automation and hiring.

On stage, Brady’s remarks closely mirrored that approach. He consistently framed Amazon’s robotics strategy as one of augmentation, not replacement, describing new systems as tools built for people.

In the follow-up interview, Brady said he disliked the term “artificial intelligence” altogether, preferring to refer to the technology simply as “machines.”

“Intelligence is ours,” he said. “Intelligence is a very much a human thing.”

Follow-up: Alaska Airlines will ‘diagnose our entire IT infrastructure’ after latest outage disrupts 49,000 passengers

Alaska Airlines is still working to restore operations following a major outage that forced the Seattle-based company to cancel more than 360 flights on Alaska and its subsidiary Horizon Air.

The outage began Thursday around 3:30 p.m. PT. Alaska grounded planes across the U.S. as it addressed what it described as a “significant IT outage.”

In a statement, Alaska said a “failure occurred at our primary data center.” The outage was not a cybersecurity incident, according to the company.

“The IT outage has impacted several of our key systems that enable us to run various operations, necessitating the implementation of the ground stop to keep our aircraft in position,” Alaska said. “The safety of our flights was never compromised.”

The ground stop was lifted at 11:30 p.m. PT Thursday, but the company is still actively addressing operational impacts that resulted from the disruption.

The company canceled its planned third quarter earnings call on Friday. “We do not yet have an estimate of the financial impact of the operational disruption on our fourth quarter results,” Alaska said in a regulatory filing. The company reported revenue of $3.8 billion, up 1.4% year-over-year, while profit dropped 69% to $123 million.

The impact of the outage was evident at Sea-Tac Airport on Thursday evening, where long lines wrapped around the concourse and a maze of suitcases piled up in the baggage claim area.

The company’s Hawaiian Airlines subsidiary was not affected.

Alaska encouraged customers to check their flight status before heading to the airport, and flagged its flexible travel policy.

It’s Alaska’s second outage in three months. The Seattle-based airline grounded flights after an IT outage in July that lasted about three hours.

When Tim Chen tried to break into venture capital six years ago, multiple firms in Seattle turned him down. “Nobody wanted to hire me,” he recalled in an interview with GeekWire. “I was too technical, they said. Too nerdy.”

Chen, a University of Washington graduate and infrastructure engineer who had just sold a startup, decided to launch his own firm.

Six years later, Chen’s investors — known as limited partners, or LPs — line up to give him money before he even opens a pitch deck.

Chen recently raised $41 million for a fourth fund at Essence VC, his venture firm that backs infrastructure startups. His LPs include institutional investors such as Andreessen Horowitz’s Martin Casado and Cendana Capital’s Michael Kim.

TechCrunch described Chen as “one of the most sought-after solo investors,” highlighting how investors preempted the latest fund.

“I had no deck, no memo — I hadn’t even started raising,” Chen told GeekWire. “The LPs just all came in.”

Chen used AngelList to raise $1 million for his first fund in 2019, focusing on developer tools and infrastructure — categories he knew inside out. The experiment quickly snowballed: he raised $5 million for Fund II and $27 million for Fund III.

A dozen companies from the Essence portfolio have been acquired, including Tabular, a data management startup that sold to Databricks last year for a reported $2.2 billion.

What started as rejection has become a calling for Chen — and an unconventional venture capital success story.

After studying computer science at the UW, Chen worked at Microsoft and VMware, helped launch open-source cloud startup Mesosphere, and later founded Hyperpilot, an “AIOps” company acquired by Cloudera.

Chen’s experience as a software engineer and operator has become his edge in VC — especially amid the AI boom. He’s able to make faster decisions and gain respect from founders.

“Tim asked the hardest, most interesting questions about how we were going to build what we said we were going to build,” said Jordan Tigani, CEO of Seattle startup MotherDuck. “From a founder perspective, this let me trust that he actually believed in what we were doing and was coming to his decisions on his own.”

Seattle entrepreneur Patrick Thompson raised capital from Chen twice — with his previous startup Iteratively, which was acquired, and his current company Clarify. “He’s one of the most technically-minded people, but also super humble and easy to work with,” Thompson said.

The combination of engineering depth and empathy has helped Chen win competitive early-stage deals. He’s built a niche around helping technical founders translate research and code into products and go-to-market strategies.

“I’m looking for people that have a deep enough background, with high intensity, and huge flexibility on learning,” he said.

Essence’s portfolio spans across the U.S. and beyond. LPs ask Chen why he hasn’t moved to the Bay Area yet.

Chen is staying in Seattle, where he’s lived since high school. He believes Seattle’s tech scene is under-networked but brimming with talent.

“There’s so much great engineering talent with great iconic companies here,” he said.

Essence plans to make around 40 investments out of its fourth fund. Seattle is certainly on Chen’s radar.

“Of course,” he said. “I’m meeting people here, like UW PhDs. I like technical people. The nerdier, the geekier, the better.”

Updated at 8:40 p.m. Pacific.

Alaska Airlines said it’s recovering from an IT outage and “actively restoring operations” as of 7 p.m. Thursday after grounding flights across the U.S. for about three hours.

In a statement sent to GeekWire, Alaska said the outage began around 3:30 p.m. PT with a failure at the company’s primary data center.

“The IT outage has impacted several of our key systems that enable us to run various operations, necessitating the implementation of the ground stop to keep our aircraft in position,” the company said. “The safety of our flights was never compromised.”

The outage was not a cybersecurity event or related to other events, according to Alaska.

Flights are resuming but passengers at some airports are facing long delays as they await inbound planes.

During the outage, passengers on Reddit reported that some planes were sitting on the tarmac or de-boarding. Customers also reported issues with the company’s app and website.

It was Alaska’s second outage in three months. The Seattle-based airline grounded flights after an outage in July that lasted about three hours.

Alaska Airlines is experiencing an IT outage affecting operations. A temporary ground stop is in place. We apologize for the inconvenience. If you're scheduled to fly tonight, please check your flight status before heading to the airport.

— Alaska Airlines News (@AlaskaAirNews) October 23, 2025

100 fewer Alaska Airlines aircraft in the air now compared to last week as the airline is experiencing an IT outage this evening. Some flights are now departing, but a delays will be felt for some time to come. pic.twitter.com/zIkJTTETiz

— Flightradar24 (@flightradar24) October 24, 2025

Hanging out with my Alaska homies on the tarmac at SEATAC
byu/DripIntravenous inAlaskaAirlines

How will the companies that have invested tens of billions of dollars in the infrastructure for artificial intelligence fare when the enshittification hits the fan? That question came in for a lot of attention — and snark — when tech pundits Cory Doctorow and Ed Zitron sat down in Seattle to muse about what’s happening in the world of AI.

Both men know a thing or two about enshittification, the process by which tech offerings gradually turn to crap due to the hunger for profits.

Doctorow’s Seattle stopover was part of a publicity tour for his newly published book on the subject, “Enshittification: Why Everything Suddenly Got Worse and What to Do About It.” For Wednesday night’s appearance at the Seattle Public Library, he was paired with Zitron, a public relations specialist, podcaster and writer who surveys the tech scene with a critical eye.

The way they see it, the bursting of the AI investment bubble is a given. And that’s not by any means a contrarian view. Even Microsoft CEO Satya Nadella and Amazon founder Jeff Bezos have acknowledged that the AI tech sector seems likely to go through some retrenchment, while insisting it will be followed by a resurgence that will bring huge benefits to society.

That’s where Doctorow and Zitron part ways with Nadella and Bezos.

“This cannot succeed,” Zitron said. “On top of the fact that everyone’s unprofitable, it’s not actually that popular, either. ChatGPT is very popular because a lot of people love being driven insane. … People will tell you AI’s coming, you must learn AI. The reason it’s not able to do your job is, it’s shit.”

Even if the bubble bursts for good, Doctorow holds out hope that there’d still be some use for the billions of dollars’ worth of AI-boosting chips that have already been purchased for power-gobbling data servers. “If you want to think about a post-AI world, imagine what you would do if GPUs were 10 cents on the dollar, if there were a lot of skilled statisticians looking for work, and if you had a bunch of open-source models that had barely been optimized and had a lot of room at the bottom,” he said.

Zitron is more pessimistic. “The thing that terrifies me about this bubble is, this is not useful infrastructure at all.”

Doctorow defended his vision of a post-AI world by citing a few examples — including AI-augmented search engines that can plow through hours upon hours of podcast audio to find a key quote and whip up a transcript, and AI models that can serve as a backstop when radiologists search through X-rays for signs of cancer.

He also pointed to a nonprofit organization called the Human Rights Data Analysis Group. “They did a project with Innocence Project New Orleans, where they used LLMs [large language models] to identify the linguistic correlates of arrest reports that produced exonerations,” he said. “They used that to analyze a lot more arrest reports than they could otherwise. And they put that on top of a funnel where lawyers and paralegals were able to accelerate their exoneration work.”

When do Doctorow and Zitron think the AI bubble will burst? “No later than Q3 2026,” Zitron said. Doctorow had a less definitive answer.

“I’m a firm believer that the market can remain irrational longer than you can remain solvent,” he said. “I would say that the number of foundation models that will be around after the crash very likely could be zero. I’m not saying that it must be zero. … You can’t kill an open-source model if people like it and contribute.”

So, what’s a techie to do? “Now is the time to unionize,” Doctorow said. He acknowledged that President Donald Trump’s moves against the National Labor Relations Board have made things more difficult for unions, but insisted that all was not lost for the labor movement.

“Trump thinks that we fired the referee, and so that means all the players have to leave the field,” Doctorow said. “He’s wrong. When you fire the referee, it means there are no more rules, right? And there’s a reason that fascists attack unions first. It’s because the opposite of fascism is solidarity.”

When asked what they would advise the next generation of techies to study, neither tech pundit mentioned computer science. “Finance,” Zitron said. “In all seriousness, finance is not as difficult or complex as it sounds, and indeed, the world runs on money.”

Doctorow passed along the advice he said he gave to his daughter. “If you don’t know what you want to do at university, don’t go to university. Go to college and become an electrician,” he said. “There’s so much work for electricians, and we are going to be solarizing for the next 40 years. … It’s like being a plumber, but you don’t have to touch poo.”

He noted that the benefits extended beyond the money. “If you want to learn more, and you like it, you can become an e-eng [electrical engineer],” Doctorow said. “And if you don’t, you can put yourself through college by being an electrician — and learn finance.”

A detailed explanation of this week’s Amazon Web Services outage, released Thursday morning, confirms that it wasn’t a hardware glitch or an outside attack but a complex, cascading failure triggered by a rare software bug in one of the company’s most critical systems.

The company said a “faulty automation” in its internal systems — two independent programs that began racing each other to update records — erased key network entries for its DynamoDB database service, triggering a domino effect that temporarily broke many other AWS tools.

AWS said it has turned off the flawed automation worldwide and will fix the bug before bringing it back online. The company also plans to add new safety checks and improve how quickly its systems recover if something similar happens again.

Amazon apologized and acknowledged the widespread disruption caused by the outage.

“While we have a strong track record of operating our services with the highest levels of availability, we know how critical our services are to our customers, their applications and end users, and their businesses,” the company said, promising to learn from the incident.

The outage began early Monday and impacted sites and online services around the world, again illustrating the internet’s deep reliance on Amazon’s cloud and showing how a single failure inside AWS can quickly ripple across the web.

Related: The AWS outage is a warning about the risks of digital dependance and AI infrastructure

For the last two years, Microsoft’s video game division has been working to meet financial targets that are well in excess of the typical industry standard, which has led to waves of layoffs, canceled projects, and a general perception that the company is scrambling.

These allegations come from a new report from Bloomberg journalists Jason Schreier and Dina Bass, who reported that Xbox has been told it’s expected to work toward a profit margin of 30% across the board.

As far as can be told from outside Microsoft, this is significantly above Xbox’s profit baseline. A typical quarterly report from Microsoft only discloses revenue, but as noted by TweakTown, Xbox head Phil Spencer testified in court in 2022 that “the Xbox business today runs at a single-digit profit margin.”

It’s worth noting that even the biggest game studios usually maintain a profit margin of roughly 20% under typical circumstances. As an example, Xbox subsidiary Activision Blizzard, which runs some of the most popular games-as-a-service in the world today, “only” had a profit margin of 22-to-25% two years ago before Microsoft’s acquisition completed.

Even Sony, Microsoft’s primary competitor in the console space and the makers of the PlayStation 5, reportedly only runs at a 9.5% profit margin. Through that lens, any video game company that’s honestly eyeing a consistent 30% is living in a dream world.

The new financial target reportedly came directly from Microsoft CFO Amy Hood in the fall of 2023, which marked the start of a series of big decisions and policy reversals at Xbox.

Since then, Microsoft has drawn fire for multiple waves of layoffs; reorganized several subsidiaries such as Halo Studios; raised the base MSRP of the Xbox Series X twice so far this year; made moves to phase out physical media; officially ported many of its hit first- and third-party games to PlayStation and Switch; and canceled multiple highly-anticipated game projects such as Rare’s Everwild, a reboot of Perfect Dark, and ZeniMax’s MMO code-named Project Blackbird.

Earlier this month, Microsoft hiked the price of its Xbox Game Pass subscription service, claiming it was part of a significant “upgrade package.” Less relevantly to consumers, it has also allegedly raised the price of Xbox development kits by $500, blaming unspecified “macroeconomic” factors.

Some of that, to be fair, is due to circumstances outside Xbox’s control such as the ongoing chaos over tariffs. This year has been a rough time to be a hardware manufacturer.

Xbox is also apparently locked into at least one more console generation, according to recent interviews with Microsoft’s Sarah Bond. The phrase that keeps coming up is “very premium, very high-end curated experience.” If the recently-released Xbox Ally is any indication, the next-gen Xbox will be something more like an expensive, user-friendly Windows PC than what we’d currently recognize as a game console.

For a while now, though, Xbox has come off like its left hand doesn’t know what the right is doing, which made little sense in the wake of reports that the division was both growing and pulling in increased revenue. If it’s being forced to contend with unrealistic expectations from higher up at Microsoft, however, that would explain the overall sense of disorganization.

This is one of the most infamous types of “creative accounting” in the video game industry: issue an inflated revenue forecast, then blame developers/titles when their games fail to reach those numbers. Square Enix notoriously came under fire for this in the 2010s with releases like the 2013 reboot of Tomb Raider. It was a solid success (3.4 million copies sold), but its publisher wanted a blockbuster, so it regarded the game as a failure. History repeats.

In theory, Xbox ought to be one of the leading voices in video games as a hobby and medium right now, but it’s being forced to burn much of its time and effort in an attempt to meet a profit goal that no company on Earth could expect to reach.

If you’re inclined to believe the rumor that’s been in circulation in Seattle this year, that Microsoft’s current leadership would like to shut down Xbox entirely so it can use those resources for more AI research, this is more data for your theory.

Seattle Mayor Bruce Harrell has a message for his city’s tech giants: it’s time to reinvest in the community.

Harrell, speaking at an event Wednesday hosted by the Fremont Chamber of Commerce, said Seattle’s large companies have a “moral obligation to give back.”

The mayor specifically called out Microsoft and Amazon, citing their annual profits. “Microsoft … they made $88 billion last year … they have an obligation to give back to society, as does Amazon,” he said.

Harrell also described Seattle as a “city of innovation,” and one that has become a “great launching pad and fertile grounds for large companies.”

“That’s a good thing,” he said. “That’s not a bad thing.”

His comments reflect a delicate balance faced by Harrell and other city leaders — ensuring that Seattle’s global tech corporations continue to bolster the economy and tax base, while addressing the ripple effects on housing, transportation, and communities.

Harrell has delivered a similar message since taking office in 2022.

“What I’ve tried to do as mayor is to say, without ambiguity, that we value their jobs,” he said of Amazon, Seattle’s largest employer, in an interview with GeekWire earlier this year. “We also believe in a culture of accountability.”

During an appearance at the GeekWire Summit in 2022, Harrell urged the business and tech industry to get more involved in civic life to help make improvements in the city.

“There’s just plenty of opportunities for you all to engage,” he said, “and I’m just a call away to facilitate that engagement.”

Harrell, a former attorney in the telecom industry, is seeking re-election next month. He’s facing off against Katie Wilson, a progressive community organizer who won nearly 51% of the vote in the August primary.

The race is drawing national attention, in part due to the contrasting profiles and campaigns between the incumbent and challenger.

Wilson was inspired to run after Seattle voters earlier this year approved a measure creating a publicly funded social housing developer, financed by a 5% tax on salaries above $1 million paid to employees working in the city.

Harrell supported an alternative funding mechanism for social housing in Seattle. The proposed ordinance received financial support from Amazon and Microsoft.

The debate over who should pay for city services — and how much — underscores a broader tension between Seattle’s progressive tax ambitions and its reliance on the tech industry’s prosperity.

Harrell briefly spoke about taxes during Wednesday’s event, noting how the city “lost 10,000 jobs from Amazon” following years of friction over tax policy in Seattle. “That’s not a sustainable strategy, just to tax people,” he said.

However, Harrell earlier this year supported a proposal that would shield smaller companies from paying Seattle’s business & occupation tax — while increasing rates for larger companies.

Harrell was city council president in 2018 when lawmakers approved — and then repealed — a controversial per-employee “head tax” on big businesses. The council in 2020 later passed the “JumpStart” payroll tax, which Wilson helped craft.

Speaking to GeekWire last month, Wilson — whose platform is focused on raising more revenue “from the wealthiest corporations” — said she aims to have a working relationship with Amazon and other tech companies, calling them “very important players in our city and our economy.”

While tech dominates the Seattle economy, Wilson is interested in diversifying that focus. In a recent post on Reddit, she cautioned that a heavy reliance on the tech sector could pose problems for Seattle down the road.

“We’ve really been blithely riding the tech wave for the past 15 years and I don’t think we can just assume that will continue,” she wrote.

At the event Wednesday, Harrell also discussed public safety and the city’s new high-tech operations center designed to help officers fight crime in real time.

The Real Time Crime Center (RTCC) pulls live footage and data from surveillance cameras and other sources into a centralized command room staffed by analysts up to 20 hours a day.

Critics, including Wilson, have raised concerns about the federal government using surveillance footage to target immigrants.

Seattle Police Department Captain James Britt said earlier this year that data requests from outside agencies — including federal law enforcement — are screened and must comply with state and local laws. “We control where all of our data goes,” Britt said at a press event in July touting the RTCC.

Harrell reiterated the point on Wednesday, saying that third parties cannot obtain footage. He also noted other cities that have similar systems in place.

“We have actually caught criminals because of the technology,” he said.

Harrell last month announced a “responsible AI plan” that provides guidelines for Seattle’s use of artificial intelligence and its support of the AI tech sector as an economic driver.

Award-winning immunologist ​​Susan Kaech is the new executive vice president of the Allen Institute’s Immunology Moonshot, an initiative that aims to understand the immune system’s role in human health and disease.

Kaech currently leads the NOMIS Center for Immunobiology and Microbial Pathogenesis at the Salk Institute for Biological Studies and will join the Allen Institute in January.

“The appointment comes at a critical time in bioscience when the immune system is regarded as the cornerstone of all diseases and understanding its foundational principles is vital to unlocking new treatments and therapies,” the institute said in a statement.

Kaech’s research includes the investigation of how the immune system remembers infections to develop immunity, T-cell communications, and the role of metabolism in the immune system’s fight against cancer.

—  Seattle RFID company Impinj named Arthur Valdez Jr. to its board of directors.

Valdez recently left the role of executive VP of global supply chain and customer solutions at Starbucks and his career includes leadership roles at Amazon, Target and elsewhere.

“Arthur’s expertise transforming and optimizing strategic supply chain and logistics networks for large consumer-facing companies will be invaluable as we continue to advance our vision of connecting every thing,” said Impinj CEO Chris Diorio in a statement.

— Jason Bennett has taken a new role at Amazon Web Services, shifting from VP of U.S. enterprise to VP of worldwide startups and venture capital. Bennett has been with the company for more than 17 years.

On LinkedIn Bennett shared his fondness for working with startups and said he was eager to return to a position serving that community.

“I’m energized by the opportunity to work alongside our teams to support a thriving startup ecosystem — from founders and VCs, to accelerators, and the broader innovation community,” he said, adding that the work “has a lasting impact on the direction of industries and the future of AI.”

— NuScale Power named James Canafax as chief legal officer and corporate secretary. The Tigard, Ore.-based nuclear energy company is developing small modular reactors.

Canafax has decades of legal experience and joins NuScale from Maritime Partners. Past positions include executive leadership at BWX Technologies, which supplies nuclear components and services.

“[Canafax’s] extensive experience in the nuclear industry, deep familiarity with the regulatory environment and track record of guiding organizations through key growth periods make him uniquely suited to support NuScale at this important moment for our company,” CEO John Hopkins said in statement.

— Seattle entrepreneur Elvis Dieguez is now VP of data science, analytics and platforms for the healthcare startup hims & hers. Diegeuz joins the company from symphonie, a Seattle e-commerce marketing platform where he was CEO and co-founder. He was previously at Amazon for more than four years working in business analytics and as a senior manager.

Hims & hers offers a telehealth platform for conditions including sexual health, hair loss, mental health, skincare and weight loss.

“I look forward to leading and working with a ~70 person team who’ve been working hard to make the #healthcare system work for all Americans,” Dieguez said on LinkedIn.

— Biotech startup Synthesize Bio named Ariel Brumbaugh as senior director of business development. In the role, Brumbaugh will help the company partner with biopharma companies interested in using Synthesize’s AI-based research platform to accelerate and de-risk drug development.

Seattle’s Synthesize Bio was founded by leaders from Fred Hutchinson Cancer Center. Last month it announced $10 million in funding from Madrona.

Brumbaugh joined the startup from the San Francisco biotech company Gladstone Institutes.

— Sophie Brougham is director of philanthropic operations for the recently launched Clean Economy Project. Nicknamed CleanEcon, the effort includes past employees of the Bill Gates-led Breakthrough Energy and is a policy and advocacy platform promoting clean power.

Prior to Breakthrough, Brougham was with the Paul Allen holding company Vulcan (now known as Vale Group) for more than a decade, where she was a senior manager and led programs including philanthropic and grants management.

— Seattle’s Jake Laes is now executive director of AI Tinkerers, a global network of AI engineers and builders. Laes joined the group from Deel, where he helped facilitate partnerships between investors and accelerator programs. Laes is the founder of YoungTech Seattle, and his background includes mentoring and leadership roles at the University of Washington’s CoMotion and Techstars.

— Pranam Kolari, VP of search and recommendations at Coupang, is resigning from his role next month. Coupang is South Korea’s largest e-commerce platform and is headquartered in Seattle. Kolari, based in San Jose, Calif., was previously at Walmart Labs for nearly a decade where his roles included vice president of engineering for search.

— Datavault AI appointed Pete Scobell as VP of global security. The Beaverton, Ore.-based company helps businesses monetize their data and create digital twins of physical objects. Scobell is a decorated U.S. Navy SEAL veteran and will oversee Datavault AI’s security operations, risk management and asset logistics.

— Erin McHugh Saif, a former Massachusetts-based Microsoft executive, is CEO of an as-yet unnamed data and AI venture to serve “place-based partnerships,” which are networks of nonprofits, government agencies, and educational entities that aim to address education, jobs and housing needs.

“With better access to data, these organizations will leap ahead in this moment of AI transformation, gaining faster insight into which programs deliver the greatest improvement to significantly scale their impact,” Saif said on LinkedIn.

The effort has the support of the Ballmer Group, a philanthropic organization co-founded by former Microsoft CEO Steve Ballmer and his wife Connie, and the nonprofit TechSoup.

— Karen Ng was promoted to executive VP of product at HubSpot. Ng has been with the company since 2022, joining as senior VP of product and partnerships. Past employers include Common Room, Google and Microsoft, where she was chief of staff across the company’s developer tools business. Ng is based in the Seattle area.

Seattle-area cybersecurity startup Chainguard landed $280 million in new financing, just six months after a Series D round pulled in $356 million.

The new funding, announced Thursday, comes from General Catalyst’s Customer Value Fund (CVF).

Founded in 2021, Chainguard aims to help customers secure their “software supply chain,” a term used to describe a company’s software production line.

Chainguard focuses on helping companies keep their open source software secure and offers tools to manage container images, a core code component of cloud-based applications. It has more than 200 customers, including ANZ Bank, Canva, GitLab, Hewlett Packard Enterprise, VPBank, and Wiz.

Technically based in Kirkland, Wash., the remote startup employs more than 500 people and has raised $892 million to date as its valuation has risen to $3.5 billion. The company is ranked No. 3 on the GeekWire 200 index of the Pacific Northwest’s top startups, and Chainguard recently landed on LinkedIn’s list of the top 50 startups in the U.S. (at No. 18).

In fiscal year 2025, Chainguard says it grew its annual recurring revenue seven times to $40 million.

CEO and co-founder Dan Lorenc said the funding will help accelerate the adoption of Chainguard across more companies.

“Open source powers the world, but the way it’s delivered and deployed often introduces risk,” Lorenc said in a statement. “At Chainguard, we’re flipping that script: we guard open source from all the things that can go wrong with it, so engineering teams can build anything they want with it.”

Chainguard CFO Eyal Bar said the partnership with General Catalyst enables Chainguard “to scale go-to-market investment without diluting ownership or slowing innovation.”

Instead of using equity to fund sales and marketing spend, General Catalyst provides structured growth capital tied directly to customer acquisition and recurring revenue. The goal is to let startups like Chainguard preserve equity while using outcome-based financing to scale efficiently.

Previous Chainguard investors include Amplify, IVP, Kleiner Perkins, Lightspeed Venture Partners, Mantis VC, Redpoint Ventures, Sequoia Capital, and Spark Capital.

Previously:

• Cybersecurity startup Chainguard lands $356M at $3.5B valuation, up from $1.1B a year ago
• Chainguard doesn’t have an office. Here’s how the $3.5B cybersecurity startup makes remote work.

Microsoft is rolling out a series of updates to its consumer Copilot AI assistant, including shared group chats, long-term memory, and an optional visual persona named Mico.

New capabilities include a “real talk” conversation style, a Learn Live feature that acts as a voice-enabled Socratic tutor, new connectors that link to services like Google Drive, Gmail, and Outlook, and deeper integration with Microsoft’s Edge browser.

Microsoft is competing against AI tools including Google’s Gemini, Amazon’s Alexa, Apple’s revamped Siri, OpenAI’s ChatGPT, and Anthropic’s Claude in the consumer market. 

It looks to be the single biggest Copilot update to date from the group led by Mustafa Suleyman, the Google DeepMind co-founder who joined Microsoft last year as its AI CEO. 

“This release is a milestone for what AI can deliver,” Suleyman writes in a blog post, explaining that the idea is to make Copilot a comprehensive assistant that connects users to their personal information, contacts, and tools with the goal of improving their lives.

The features are rolling out starting today in the U.S, and the company says they will be available soon in the UK, Canada, and other parts of the world. Microsoft is showing the new features in the live stream below.

Every Friday at 5 p.m., Diego Oppenheimer gets an email that remembers his week better than he does. It pulls from his calendar, meeting transcripts, and inbox to figure out what really mattered: decisions made, promises to keep, and priorities for the week ahead.

“It gives me a superpower,” said Oppenheimer, a machine-learning entrepreneur best known as the co-founder of Algorithmia, who’s now working with startups as an investor in Seattle. 

What’s notable is that Oppenheimer didn’t buy this tool off the shelf — he built it. What started as a personal experiment turned into a challenge: could he still code after years away from writing production software?

With the rise of AI-powered coding assistants, he realized he could pick up where he left off. His personal project, with the unglamorous name “Actionary,” has grown to somewhere around 40,000 lines of what he jokingly calls vibe-coded “spaghetti.” It’s messy but functional.

Oppenheimer’s do-it-yourself AI assistant is more than a novelty. It’s a window into a broader shift. Individuals and companies are starting to hand off pieces of judgment and workflow to autonomous systems — software that analyzes data, makes recommendations, and acts independently.

Exploring the agentic frontier

This emerging frontier is the subject of Agents of Transformation, a new GeekWire editorial series exploring the people, companies, and ideas behind the rise of AI agents. A related event is planned for Seattle in early 2026. This independent project is underwritten by Accenture.

For this first installment, we spoke with startup founders and DIY builders working to replicate different aspects of the work of great executive assistants — coordinating calendars, managing travel, and anticipating needs — to see how close AI agents are getting to the human standard.

The consensus: today’s agents excel at narrow, well-defined tasks — but struggle with broader human judgment. Attempts to create all-purpose digital assistants often run up against the limits of current AI models. 

“I might have my travel agent and my finance agent and my stock trading agent and my personal health coach agent and my home chef agent, etc.,” said T.A. McCann, a Seattle-based serial entrepreneur and managing director at Pioneer Square Labs, on a recent GeekWire Podcast episode. 

McCann foresees these narrow agents handling discrete tasks, potentially coordinated by higher-level AI acting like a personal chief operating officer.

But even the term “AI agent” is up for debate. Oppenheimer defines a true agent as one with both autonomy and independent decision-making. By that standard, his system doesn’t quite qualify. It’s more a network of models completing tasks on command than a self-directed entity.

“If you asked a marketing department, they would say, absolutely, this is fully agentic,” he said. “But if I stick to my AI nerd cred, is there autonomous decision-making? Not really.”

It’s part of a much larger trend. The market for AI workplace assistants is projected to grow from $3.3 billion this year to more than $21 billion by 2030. according to MarketsandMarkets. Growth is being driven both by enterprise giants such as Microsoft and Salesforce embedding agents into workplace software, and by startups building specialized agents. 

A report by the newsletter “CCing My EA,” citing an ASAP survey, notes that 26% of EAs now use AI tools. Some fear job loss due to AI, but most top EAs see AI as an augmentation tool that frees time for strategic work. 

From summaries to scheduling

One company exploring this emerging frontier is Read AI, a Seattle-based startup known for its cross-platform AI meeting summarization and analysis technologies, which has raised more than $80 million in funding.

Co-founder and CEO David Shim revealed that Read AI has been internally developing and piloting an AI executive assistant called “Ada” for tasks including scheduling meetings and responding to emails.

Ada replies so quickly that Read AI has been working on building in a delay into the email response time so that it seems more natural to the recipients.

Shim has been personally testing the limits of the technology — giving Ada access to a range of workplace data (from Outlook, Teams, Slack, JIRA, and other cloud services) and letting the assistant autonomously answer questions about Read AI’s business that come in from the company’s investors in response to his periodic updates.

“It answers questions that I would not have the answer to right off the bat, because it’s not just pulling from my data set, but it’s pulling in from my team’s data set,” Shim said during a fireside chat with GeekWire co-founder John Cook at a recent Accenture reception.

Shim laughed, “I’m willing to take that risk. We’re doing well, so I don’t mind giving out the data.” 

However, there are limitations. Ada can struggle with complex multi-person scheduling or tasks requiring data it can’t access, and can still occasionally hallucinate. To manage this, ReadAI incorporates human oversight mechanisms like “sidebars” where Ada asks for confirmation before sending replies to messages deemed more sensitive or difficult. 

Shim argues against the idea of building a single, all-encompassing agent. 

“The approach of agents doing everything is not the right approach,” he said. “If you try to do everything, you’re not going to do anything well.”

Instead, he believes successful AI assistants will focus on solving very specific problems, much like Google Maps gives driving directions without trying to be a general travel agent. 

The “book-me-a-hotel” challenge

Travel is a use case that’s close to the heart of Brad Gerstner, founder and CEO of Altimeter Capital. Gerstner is known for backing some of the biggest names in tech — from Snowflake to Expedia — and for distilling big tech shifts into simple tests, such as his hotel booking challenge.

The specific example he gave at the 2024 Madrona IA Summit in Seattle was telling an AI agent to book the Mercer Hotel in New York on a specific day at the lowest price — a common challenge for business travelers.  

“Until we can do that, we have not built a personal assistant,” he said. 

That’s part of the larger problem Michael Gulmann, a former Expedia product executive, set out to solve with the startup Otto, which is developing an AI agent specifically for business travelers.

As shown publicly for the first time at this year’s Madrona conference, Otto tackled Gerstner’s specific challenge. After receiving the request to book the Mercer Hotel on a specific day, it found the cheapest available room, confirmed the price and details, and completed the booking, with minimal prompting, within about two minutes.

“Who would have thought that Brad Gerstner wanted the cheapest room?” Gullman joked.

Otto handles various aspects of travel. It understands and learns detailed user preferences — from specific amenities like rooftop bars to preferred airline seats, hotel room types, and loyalty programs — using this knowledge to refine searches and make personalized recommendations. 

As Gulmann explained in an interview, Otto doesn’t use a single monolithic model. It coordinates a bunch of narrow agents: one to interpret messages, another to manage loyalty programs, another to handle payments. Together they simulate a small operations team working behind the scenes.

Otto confirms details with the user before completing purchases, even though it could do that autonomously. Gulmann described that precaution as psychological, not technical — knowing that most people aren’t yet comfortable with AI buying things without their involvement.

After learning about Otto’s capabilities, Gerstner was impressed and wanted to see how it performs as it moves into public beta, said Mike Fridgen, a venture partner at Madrona, which incubated the company.

The grand challenge of scheduling

If hotel booking is the acid test for autonomous assistants, scheduling meetings is the everyday nightmare.

That’s the problem Howie is trying to solve. The Seattle startup’s AI assistant lives in the email inbox. CC Howie on a thread, and it proposes times, confirms with all parties, creates invites, and adds meeting links.

Howie works from a detailed “preferences document,” inspired by how experienced executives train their human EAs — which cafés are acceptable for meetings, how late is too late on Fridays, etc.

The company recently launched publicly with $6 million in funding and a growing number of paying customers. It uses a hybrid model: AI supported by human reviewers. That helps avoid the tiny errors that destroy trust — mixing up time zones, dropping a name from a thread, or misreading social cues.

The system simulates decisions internally, flags potential errors for review, and escalates anything ambiguous to a human before hitting send. 

“If you think about the things that a great human EA does, software is not replacing that anytime soon,” said Howie co-founder Austin Petersmith.

In fact, Petersmith said, many of Howie’s users are human EAs themselves, using it to offload logistics. “Nobody wants to do scheduling,” he said. “Everybody wants the machines to take this particular task on.”

As models improve, Petersmith hopes Howie can expand into other “meta-work” — the administrative overhead that keeps knowledge workers from the higher-value activities that are still the realm of humans.

More time in the day

For Diego Oppenheimer, this isn’t a hypothetical issue. “I’m extremely calendar dyslexic,” he explained. “I’ll triple-book myself. I’ll agree to go to places I shouldn’t be. I’ll travel to the wrong city. Really bad.”

Over the years, he relied on human EAs and a chief of staff to keep him on track. But when he stepped back from running a company full-time, hiring someone just to manage his complex, multi-role calendar no longer made sense. So he built Actionary to help. It sends the Friday recap to catch him up on the week, flagging issues right before his weekend “reboot.”

Oppenheimer’s project won the People’s Choice Award at an AI Tinkerers event in New York last month. But he is very clear: Actionary is a personal project, not a product in the making. He developed it for himself, and can’t imagine taking on the headache of feature requests and technical support from others.

He’s bullish on the larger trend, and a user and investor in tools like Howie. But he also recognizes that AI agents can’t match the comprehensive skills and judgment of a human EA, let alone a chief of staff in a higher-level strategic role.

Oppenheimer’s ultimate goal is more straightforward, but still ambitious. “I’m trying to make time in the day,” he said. “That’s what I’m trying to do.” 

GeekWire’s Todd Bishop reported and wrote this article with editing assistance from AI tools including Gemini and a custom OpenAI GPT trained in GeekWire’s editorial approach. All facts, quotes, and conclusions were reviewed and verified prior to publication.

Seattle agriculture-tech startup Carbon Robotics raised $20 million in new funding to support the creation of another piece of AI-powered machinery for farms.

With its signature LaserWeeder and relatively new Autonomous Tractor Kit (ATK) already being used by hundreds of customers, Carbon founder and CEO Paul Mikesell told GeekWire that “a brand new AI robot” is coming.

Mikesell said the machine, which is at least nine months away from being revealed, will leverage the same AI system used in Carbon’s other equipment but perform tasks beyond weeding.

“It’s very flexible, capable of doing a lot with the world around it, understanding what it’s seeing, what’s happening,” Mikesell said of Carbon’s system that uses an array of AI, computer vision and machine learning technology. “We see our ability to reinvest in that platform and double down on what it can do in some new activities.

“It’ll blow your mind,” he added.

Founded in 2018, Carbon Robotics made its name across ag-tech with the LaserWeeder, a machine which can be pulled behind a tractor and uses its tech to detect plants in fields and then target and eliminate weeds with lasers. The latest iteration, the LaserWeeder G2, was released in February.

In March, the company unveiled the Carbon ATK, previously called the AutoTractor. That autonomous platform is designed to fit on and control existing farm equipment and serve as an answer to labor shortages and increased productivity in farming.

Both platforms are continuing to grow and scale, and “things are moving really fast,” according to Mikesell, a longtime technologist and entrepreneur who previously co-founded data storage company Isilon Systems.

LaserWeeders are active on farms across the U.S. and in 14 countries around the world. Mikesell said revenue continues to grow every year, but Carbon is not yet profitable.

Ranked No. 9 on the GeekWire 200 list of top privately held startups based across the Pacific Northwest, Carbon has previously been backed by NVIDIA and Seattle-based Voyager Capital.

The Series D-2 extension round attracted Giant Ventures as lead investor. The UK-based VC invests across a variety of “purpose-driven” startups, and Mikesell said, “They got what we were trying to do.”

Giant previously invested in a $140 million round for Tidal Vision, a Bellingham, Wash.-based company turning discarded crab shells into a valuable industrial chemical called chitosan.

Beyond the secretive new machine, Carbon is revealing more about the “large plant model” at the heart of how it does computer vision through its AI systems.

Mikesell said the company is at the point where it has enough training data and labeled images that it can teach its AI to learn about the basic structure of the plants it’s seeing. This allows Carbon to run one model on every machine in the world.

“If new weeds pop up in an onion field in France, and those are eventually going to show up in a carrot field in the U.S., the first time we see that weed anywhere it can be part of the model and be ready to go,” Mikesell said. “It also means that if we want to go into a new crop that we’ve never seen before, we can do it immediately.”

A LaserWeeder is designed to target the meristem of a weed to kill it as quickly as possible and the large plant model helps it understand where to precisely target its zap.

Carbon Robotics, which has raised $177 million to date, now employs about 260 people. The company runs a manufacturing facility in Richland, Wash., and added another in the Netherlands to offset some trade and tariff issues as well as speed deployment of machines in Europe.

Mikesell said as far as competition, there are some companies in Europe who claim to be building some version of a LaserWeeder, but he’s never seen one in a field or competed against one.

“It’s very hard to create a LaserWeeder,” he said. “The targeting system is so special, and the AI is so special. It’s not just about detecting where the weeds are. The trick to making it work is you need a targeting camera to be able to keep the lasers on target [while moving], and everybody I’ve seen that says they’re gonna build a LaserWeeder doesn’t understand that concept.”

Hyphen AI, a new Seattle-based startup using generative AI to help developers deploy cloud applications, raised $5 million in a seed round led by Unlock Venture Partners.

The company’s product, Hyphen Deploy, aims to make cloud infrastructure setup as simple as describing what an app should do.

The product automates complex DevOps processes — replacing YAML files, Dockerfiles, and Terraform modules with natural language prompts and business rules. Developers can describe service goals such as latency, scale, or compliance, and the platform automatically generates production-ready cloud infrastructure across providers such as AWS, Google Cloud, Azure, and Cloudflare.

“Today infrastructure automation typically takes weeks to setup and configure and then monthly maintenance on those configurations — Deploy reduces it to minutes,” Jared Wray, CEO and founder at Hyphen AI, said in a statement.

Wray previously founded Tier 3, a Seattle-area enterprise cloud startup acquired by CenturyLink (now Lumen Technologies) in 2013. He spent two years as an exec at CenturyLink and was later CTO at streaming company iStreamPlanet and clean tech startup Palmetto.

Hyphen joins a growing number of startups using generative AI to automate infrastructure work, including fellow Seattle startup Pulumi.

Unlock Ventures partner Andy Liu, who is based in Seattle, said the market “desperately needs” a “truly developer-first operations platform.”

“Deploy returns software development to the promise of developers leading the way with no infrastructure overhead, just focus on code,” Liu said in a statement.

Wray declined to disclose the company’s revenue metrics. He said customers have been using the platform for the past five months. Hyphen employs 10 people, including Jim Newkirk, who is serving as a fractional COO and was also an exec at CenturyLink and Tier3.

Seattle-based venture capital firm Ascend also participated in the seed round.

Unless you’ve been on a “digital cleanse” this week, you know that Amazon Web Services (AWS) had a major outage at the start of the week.

You know this because apps and sites you use were down. Credible reports estimate at least 1,000 sites and apps were affected. Large swaths of modern digital life went dark: from finance (Venmo and Robinhood) to gaming (Roblox and Fortnite) to communications (Signal and Slack). Some people couldn’t even get a good night’s sleep because the outage took out “smart beds.” Even sporting events were impacted when Ticketmaster failed.

We’ve seen outages before, but this one seemed broader and harder to ignore.

In the wake of the outage, many well-intentioned hot takes boiled down to: “They should’ve used more cloud providers.”

Setting aside the subtle victim-blaming, there’s also the fact that in a world with only three major cloud providers (AWS, Microsoft Azure, Google Cloud) if you want to “diversify” there’s not a lot of diversity out there.

And the argument for diversity in cloud providers is really about market diversity, not individual organizations juggling multiple vendors. More competition in the cloud market would mean fewer cascading failures when one provider goes down.

The key question when something like this happens is whether we’re taking the risk lessons and expanding them beyond the immediate problem to see the emerging problems. 

Instead of saying organizations need to have multiple cloud providers, we should be asking how we’re dealing with the reality of highly concentrated risks with exceptionally broad impact because we just had an object lesson in what that really means.

In this recent outage there’s a pointer to where we should be looking proactively to apply this lesson: generative AI. This recent AWS outage gives us two lessons for the emerging generative AI ecosystem.

Concentration crisis in AI

With the generative AI ecosystem, I’m talking not about chatbots — I mean AI-native applications that are built on generative AI as a platform. We just saw that when there’s no cloud, there’s no cloud-native application. Likewise, when there’s no generative AI provider, there’s no AI-native application.

The first lesson from the AWS outage for AI-native applications is what happens to an industry when there’s a limited number of providers for centralized resources and there’s an outage. We just saw: it has huge rippling effects across the industry and all walks of life built on it.

It’s a throwback to the mainframe era: when “the computer” is down, it’s down for everyone.

There are as few, if not fewer, generative AI providers as there are cloud providers. A major outage is inevitable — that’s just engineering reality. When that happens, every AI-native app built on that generative AI platform will also go down, full stop.

The impact could be even more severe than the AWS outage. It will be more like “the computer is down, and the people are gone” for many different industries and services. Ironically, the “smarter” the industry and service, the greater the potential fallout.

The second lesson is one of intertwined risk. OpenAI itself was affected by this week’s AWS outage. 

That means AI-native apps have double exposure to the risks around a limited number of providers for critical, centralized resources. For AI-native apps, it’s like the mainframe era squared. If the generative AI platform fails, everything built on it fails. And if the cloud that hosts the AI platform fails, it all goes down, too.

This is not to say don’t do cloud or don’t do AI. But it is to say we need to understand this new, complex intertwining of risks inherent in a world where everything is relying on a small number of key providers and that small number of key providers also rely on a small number of key providers.

The realities of physical requirements and capital investment required for cloud and generative AI make a truly diverse ecosystem impracticable for either. I don’t think anyone sees more than a literal handful of providers for either of these in the future. 

The bottom line

Highly concentrated risks with exceptionally broad impact aren’t going away anytime soon. 

But the growth of generative AI providers — and their reliance on cloud providers — show where there is going to be growth and where and what those risks will be. The growth will be upwards, as technologies stack on top of and rely on each other. And that means these risks are only going to become more concentrated and the impacts even broader.

In the world of security, there’s the “CIA” triad: “confidentiality”, “integrity” and “availability.” In the first days of “Trustworthy Computing” at Microsoft, the principles included “availability.” But in recent years, availability has been overlooked often as security and privacy concerns understandably dominate.

A thoughtful application of the AWS outage tells us that outages like this are a kind of problem that isn’t an anomaly: it’s inherent in the nature of today’s technology reality. And since there are no easy solutions and only increasingly complex problems around this, we need to start understanding this new reality and thinking seriously about how to mitigate these risks.

MILPITAS, Calif. — Amazon is bringing delivery details directly to drivers’ eyeballs. 

The e-commerce giant on Wednesday confirmed that it’s developing new augmented reality glasses for delivery drivers, using AI and computer vision to help them scan packages, follow turn-by-turn walking directions, and capture proof of delivery, among other features. 

Amazon says the goal is to create a hands-free experience, making the job safer and more seamless by reducing the need for drivers to look down at a device.

Scenarios shown by the company make it clear that the devices activate after parking, not while driving, which could help to alleviate safety and regulatory concerns.

[Update, Oct. 23: Amazon executives said in briefings Wednesday that the glasses will be fully optional for drivers, and they’re designed with a hardware-based privacy button. This switch, located on the device’s controller, allows drivers to turn off all sensors, including the camera and microphone.

From a customer perspective, the company added that any personally identifiable information, such as faces or license plates, will be blurred to protect privacy.

Overall, Amazon is positioning the glasses as a tool to improve safety and the driver’s experience. We had a chance to try the glasses first-hand this week, and we’ll have more in an upcoming post.]

The wearable system was developed with input from hundreds of drivers, according to the company. It includes a small controller worn on the driver’s vest that houses operational controls, a swappable battery for all-day use, and a dedicated emergency button. 

The glasses are also designed to support prescription and transitional lenses. Amazon says future versions could provide real-time alerts for hazards, like pets in the yard, or notify a driver if they are about to drop a package at the wrong address.

According to Amazon, the smart glasses are an early prototype, currently in preliminary testing with hundreds of drivers in North America. The company says it’s gathering driver feedback to refine the technology before planning a broader rollout.

The announcement at Amazon’s Delivering the Future event in the Bay Area today confirms a report by The Information last month. That report also said Amazon is developing consumer AR glasses to compete with Facebook parent Meta’s AI-powered Ray Ban smart glasses.

The enterprise AR market is in flux, with early mover Microsoft pivoting away from HoloLens hardware, creating an opening for players like Magic Leap and Vancouver, Wash.-based  RealWear.

A demo video released by Amazon shows a delivery driver using augmented reality (AR) glasses throughout their workflow. It begins after the driver parks in an electric Rivian van, where the glasses overlay the next delivery address directly onto a view of the road.

“Dog on property,” the audio cue cautions the driver. 

Upon parking, the driver moves to the cargo area. The AR display then activates to help with sorting, with green highlights overlaid on the specific packages required for that stop. As the driver picks each item, it’s scanned and a virtual checklist in their vision gets updated.

After retrieving all the packages from the cargo hold, the driver begins walking to the house. The glasses project a digital path onto the ground, guiding them along the walkway to the front door. 

Once at the porch, the display prompts the driver to “Take photo” to confirm the delivery. After placing the items, the driver taps a chest-mounded device to take the picture. A final menu then appears, allowing the driver to “Tap to finish” the stop before heading back to the van.

Seattle and the Nordic nations have strong ties — from Norway’s first astronaut launching on a SpaceX mission to Scandinavian companies supporting the efforts to electrify the region’s ferries. And those connections stretch back more than a century when John Nordstrom, a Swedish immigrant, co-founded an eponymously named shoe store in Seattle’s downtown.

“As we look towards the future, we build on our history and also our heritage. But today, we reach for much more. We are partners in innovation, from high tech in the AI revolution to building more security projects,” said Anniken Huitfeldt, Norway’s ambassador to the United States.

On Tuesday evening, Huitfeldt helped kick off the annual Nordic Innovation Summit, held in Seattle’s Ballard neighborhood at the National Nordic Museum.

The event continues through Wednesday and features speakers and panelists discussing clean energy topics such as data center operations, microgrids and recycling; cyber security initiatives; innovation in biotech; and sustainable transportation.

“We’ve seen innovations come out of the summit,” said Seattle City Councilmember Dan Strauss, speaking Tuesday. “The ability to integrate technology into new business practices is something that has happened here before, and I’m excited to see it occur here again.”

Other speakers at the opening session included University of Washington Nobel Laureate David Baker, who shared new research published since he received his award from the Swedish institution one year ago. Baker is leading efforts that harness AI to create proteins that can be used in health care, environmental cleanup and other challenges.

Norwegian Astronaut Jannicke Mikkelsen livestreamed a presentation from Oslo to share the story of her journey to space, which began at age 10 when she had a devastating horse riding accident. During a five-year recovery, Mikkelsen became obsessed with NASA — even calling the agency’s Johnson Space Center seeking employment as a 12-year-old.

“It cost us a fortune,” she said. “My dad can’t afford to drive his car to work for a week because we can’t afford gas because I called the U.S. and I applied for a job.”

Mikkelsen ultimately pursued a career in 3D photography and 3D filmmaking, residing in Svalbard, a frozen tundra that ranks as one of the world’s northernmost inhabited areas.

“This is a place that equipped me the best to become an astronaut, because it’s sort of fear-based learning,” she said. “As soon as you leave town, any mistake you make could potentially kill you. It’s exceptionally cold. There is no communication to the outside world as you leave town.”

In March of this year, SpaceX — which has significant manufacturing operations in the Seattle region — launched Mikkelsen and three other non-governmental astronauts on the first crewed orbit over the Earth’s polar regions. The Fram2 mission spanned 3½ days. The astronauts performed scientific research, including data collection on the Northern Lights, which are beautiful but poorly understood and can destroy satellites.

Mikkelsen highlighted the importance of the collaboration between nations.

“We have four non-American astronauts on board an American spaceship. This, to me, just shows great trust that the U.S. showed in us,” she said. “But it’s also American technology that flew the first Norwegian astronaut into space.”

Speakers participating in the summit on Wednesday include Mathias Sundin, founder of the Warp Institute Foundation; Douglas Kieper, director of the Paul G. Allen Research Center; Nick Huzar, co-founder of OfferUp; Sunil Gottumukkala, CEO of Averlon; Petri Hautakangas, CEO of Tupl; Maiken Møller-Hansen, director of energy and sustainability for Amazon Devices; and other corporate, government and academic leaders.

Hest, the Seattle-based maker of sleeping gear for outdoor enthusiasts, raised $2.7 million in Series A funding this month as the company sees continued growth.

The initial close was backed by existing investors — Ascend, Cascade Seed Fund, Alliance of Angels, and a number of Seattle-area angel investors — and Hest is opening the round to new investors with a final close later this year.

Founder and CEO Aaron Ambuske told GeekWire that Hest continues to experience significant growth with a 50% increase in sales this year. The startup expects to turn an operating profit for the first time.

Ambuske said the growth is driven by an expanded product line and an increase in sales at REI, where Hest is now in all stores. The company also has a partnership with electric vehicle maker Rivian.

The fresh cash will be used to support future growth opportunities.

“We are launching a new product category in 2026, expanding our partnership with Rivian and investing in new sales channels,” Ambuske said. “We recently launched in Japan and will continue to explore international options when they are a fit.”

He added that while tariffs imposed by the Trump administration “have been a lot to navigate,” over half of Hest’s cost of goods and final assembly are in the U.S., so the company has been “slightly insulated from the turbulence.”

Ambuske, who spent 18 years at K2 Sports, launched Hest in 2019 to satisfy his desire to bring a more comfortable sleeping experience to car and tent campers.

Based in Seattle’s Georgetown neighborhood, Hest opened its first showroom this summer. The company employs 10 people.

This story originally appeared on Real Estate News.

Soon after Zillow announced it was the first real estate company to launch an app in ChatGPT, some in the industry responded with alarm.

The core concern was whether the integration violates licensing rules, but the conversations touched on broader issues: How should listing data be used and controlled? How should the industry be thinking about data standards in the context of emerging AI technologies?

‘At the forefront of generative AI adoption’

In its Oct. 6 announcement, Zillow said ChatGPT users could now add the Zillow app to the popular AI chatbot and explore listings using natural language search. The app — within ChatGPT — can then display property info with links back to the original listings on Zillow. 

The integration was designed to bring “simplicity to the home journey within ChatGPT,” said David Beitel, Zillow’s chief technology officer. The partnership, he added, “puts Zillow at the forefront of generative AI adoption.”

‘What is reasonable control’ of data?

Almost immediately, some people wondered whether Zillow was following the terms of its IDX data licensing agreements with multiple listing services.

“Zillow’s ChatGPT integration raises the question: what is reasonable control of the display of MLS data?” Leah Ingalsbe, executive vice president of MLS and technology at the Greater Springfield Board of Realtors, wrote on LinkedIn. 

“Granted, licensing agreements differ from one MLS to another, but this development offers plenty of food for thought on emerging technologies that were nonexistent when many of our terms of use were penned,” Ingalsbe wrote.

She did not respond to a request for further comment.

No ‘permission to share’

A Texas real estate agent was more definitive in his stance. Danny Frank, an agent at JLA Realty and a former chair of the Houston Association of Realtors, wrote a blog post expressing his concerns, and in an interview with Real Estate News, said he believes Zillow is in violation of IDX rules.

“The brokers give permission to HAR, and they do not have my permission to share that [listing data] with another third party site, unless everyone has equal access to that,” Frank said. “Right now, only Zillow has access to that [ChatGPT integration], and they’re using that to their benefit.” 

Frank has also filed a complaint with HAR, which told Real Estate News, “We are reviewing the matter and will take appropriate action if any issues are identified.”

Who’s displaying the listings?

The National Association of Realtors’ IDX policy requires all displays of IDX listings to “be under the actual and apparent control of the participant [broker].”

Victor Lund, founding partner and co-CEO of real estate consulting firm WAV Group, has asserted that Zillow is violating this requirement, because its license allows the display of MLS data on Zillow.com and its mobile apps, not on another domain.

Lund contends that, “From the consumer’s perspective, they’re using ChatGPT … and simply invoking Zillow as a tool inside that environment.”

While NAR has not taken a stance on the Zillow integration, the association released a statement on Oct. 21 advising MLSs to consider “whether MLS data is being transmitted to an unauthorized party, if the displaying Participant maintains ‘control’ over their display, and if the display fulfills the disclosure and display requirements outlined in local IDX rules” when assessing compliance.

NAR also clarified that “the display of MLS data on mobile apps is permitted under the existing IDX policy.”

Zillow outlines its compliance measures

The company went through “a painstaking process” to make sure it was following MLS rules, according to Errol Samuelson, Zillow’s chief industry development officer, during a recent Real Estate Insiders Unfiltered podcast.

They also worked with ChatGPT creator OpenAI to ensure IDX data would not be used to train the AI model. “It was a deep collaboration, and they’ve been very respectful of the different industry rules and data privacy and federal laws and so on,” said Josh Weisberg, SVP of AI at Zillow, during the podcast. 

Zillow addressed some of the other industry concerns in its FAQ.

Regarding third-party display of data, the FAQ explains that after a user enters a prompt within the app, ChatGPT relays it to Zillow, which “sends a response that is displayed in the Zillow App, but that data does not go to ChatGPT” — in other words, the chatbot itself is not displaying MLS data.

As for the “participant control” requirement, the FAQ says “the Zillow App was built by Zillow to be IDX-compliant and is operated by, and controlled by Zillow, just as on the Zillow website and mobile app.”

Real Estate News reached out to Zillow multiple times for further comment and Zillow declined to speak on the record.

Opening a back door to data?

Web browsers like Google display links to Zillow listings, but they don’t create a downloadable spreadsheet of listing data. Will Zillow’s ChatGPT integration provide such a list? Yes.

Real Estate News tested this out by asking the integrated app for listings in a certain market and price range, which it displayed. After prompting the app with a series of additional questions, the app said it could “pull all the data the widget actually loaded” — meaning the data from the Zillow integration or “connector” itself. 

Ultimately, it captured data for 100 listings in a downloadable file. (See the exact prompts and responses at the end of this story.)

Lund believes this could open the door for third parties to capture listing data “and [use] it for commercial purposes” or “track and monitor listings” using an external system.

MLSs taking a closer look — but not saying much

Real Estate News repeated listing searches for several markets and sent the ChatGPT-created spreadsheets to the relevant MLSs. Some declined to comment on the record (Bright MLS, California Regional MLS) or did not respond to requests for comment (Miami Realtors MLS, BeachesMLS, UtahRealEstate.com, GSBOR).

Others, including Stellar MLS, Georgia MLS and NTREIS, said they were “discussing internally” or “still investigating” whether the Zillow-ChatGPT integration complies with IDX policies. 

But a spokesperson for North Carolina’s Canopy MLS said “the Zillow app remains compliant with our IDX rules at this time,” though they declined to comment further. 

Lund said he was “not surprised” MLSs weren’t talking publicly about the integration. “They’re in the middle of trying to understand it,” he said. “This is all brand-new information.”

Another reason MLSs might be keeping quiet?

“We’re in a very litigious time in our industry, more than I’ve ever seen it,” said Russ Cofano, co-founder and principal of Alloy Advisors and a licensed attorney. 

“I think people are going to be very cautious about taking approaches that could result in litigation, and doing their due diligence before they try to make any decisions that could create problems for other companies, whether it’s Zillow or anybody else,” Cofano said.

Cofano wouldn’t share a personal opinion on compliance, but he noted that “there may be some unintended consequences from this type of integration, and those things should be addressed so that we don’t have easy ways for people to misuse MLS data.”

A path forward?

Still, Cofano said he hoped the new app would spur MLSs to reach out to Zillow — not just to gauge compliance, but to learn from their innovation.

“If really this industry is about serving consumers, then we should be applauding Zillow … for trying to do something that exposes authorized listing data to more people in the way that we all know is coming, which is AI search and discovery,” Cofano said.

The industry gets “wrapped around the axle on this ownership of data issue, and sometimes … forget what the objective here is, and that is not to own the data, but to facilitate buyers looking at sellers’ homes for sale and doing transactions.”

A peek inside the Zillow-ChatGPT app

Here’s what happened when we tried the Zillow-ChatGPT app for ourselves — and asked it for the data.

Using an individual, paid ChatGPT account on a web browser, Real Estate News added the Zillow app to the account and asked, “Zillow, please show me for-sale listings in Orlando, Florida, priced between $0 and $400K.” ChatGPT displayed a map with red, pinned listings and their prices. 

When asked, “Can you get the data used to display the widget I’m seeing? All of it?” ChatGPT replied, “I can pull all the data the widget actually loaded (that’s the first page of results—up to ~100 listings with full details like address, price, beds/baths, sqft, lot size, lat/long, home type/status, and the Zillow URL).”

ChatGPT then said it could export those 100 listings and said it would “need to run multiple paged fetches” in order to capture every matching property. It then offered to deliver those first 100 listings as CSV and JSON files. When told to “go ahead,” it delivered those downloadable files, providing data for those 100 listings. 

When asked, “Where did you get the data for these files?” the reply was “From the Zillow connector powering the embedded map/widget you used here. When you asked for Orlando, FL homes $0–$400k, I called the Zillow tool behind the scenes; it returned the first page of listing payloads (what the widget loaded to render those cards). I saved that exact response as the raw JSON and a flattened CSV.”

Jamie Siminoff has lived the American Dream in many ways — recovering from an unsuccessful appearance on Shark Tank to ultimately sell smart doorbell company Ring to Amazon for a reported $1 billion in 2018.

But as with most entrepreneurial journeys, the reality was far less glamorous. Siminoff promises to tell the unvarnished story in his debut book, Ding Dong: How Ring Went From Shark Tank Reject to Everyone’s Front Door, due out Nov. 10.

“I never set out to write a book, but after a decade of chaos, failure, wins, and everything in between, I realized this is a story worth telling,” Siminoff said in the announcement, describing Ding Dong as the “raw, true story” of building Ring, including nearly running out of money multiple times.

He added, “My hope is that it gives anyone out there chasing something big a little more fuel to keep going. Because sometimes being ‘too dumb to fail’ is exactly what gets you through.”

Siminoff rejoined the Seattle tech giant earlier this year after stepping away in 2023. He’s now vice president of product, overseeing the company’s home security camera business and related devices including Ring, Blink, Amazon Key, and Amazon Sidewalk.

Preorders for the book are now open on Amazon.

Silkline, a Seattle startup using AI to help advanced manufacturing companies manage their supply chains, raised $4 million in seed funding, the company announced Wednesday.

Founded in 2023, Silkline aims to reduce production delays by simplifying and lowering the cost of sourcing materials from multiple suppliers. AI-enabled requests for quotes and purchase orders are among its recently released features.

The fresh cash will help Silkline accelerate its development of AI-powered capabilities.

Silkline customers include manufacturers in aerospace, energy, defense and robotics, including Starfish Space (Tukwila) and Portal Space (Bothell), as well as Vast, Castelion, H3X, K2 Space, Antares Industries, and Machina Labs.

In July, Silkline projected it would triple revenue in 2025. Since then, the company says revenue has grown fivefold year-over-year.

The company says its growth is being driven in part by a “network effect,” in which 20% of new customers are suppliers who received an RFQ generated by the Silkline platform.

“Supply chain teams in advanced manufacturing are struggling with missed production deadlines, RFQ to order management, and increasing demands from their customers,” Isaac Chambers, co-founder and CEO of Silkline, said in a statement. “This round of funding helps Silkline deliver more AI capabilities and reach further into the advanced manufacturing market so all modern hardware companies can experience a fully connected supply chain.”

Silkline currently employs five people.

The funding round was led by Origin Ventures with participation from Forward Deployed VC, 25madison, Matchstick Ventures, Barrel Ventures, and Plow Ventures.

SAN FRANCISCO — Facing renewed threats of federal intervention from President Trump, Mayor Daniel Lurie used an appearance at an Amazon event Tuesday to make the case that San Francisco is “on the rise,” citing its AI-fueled revival as proof of a broader comeback.

Without naming Trump or explicitly citing the proposal to deploy the National Guard, Lurie pushed back on the national narrative of urban decline — pointing to falling crime rates, new investment, and the city’s central role in the AI boom.

Lurie, who took office earlier this year, said San Francisco is “open for business” again, name-checking OpenAI and other prominent companies in the city as examples of the innovation fueling its recovery. Mayors of other cities, he said, would die to have one of the many AI companies based in San Francisco.

“Every single metric is heading in the right direction,” Lurie said, noting that violent crime is at its lowest level since the 1950s and car break-ins are at a 22-year low, among other stats.

He was speaking at the San Francisco-Marin Food Bank, as Amazon hosted journalists from around the country and the world on the eve of its annual Delivering the Future event, where the company shows its latest robotics and logistics innovations. 

“I want you to tell everybody, wherever you come from, that San Francisco’s on the rise,” he said. “You tell them there’s a new mayor in town, that we’ve got this, and we do.”

Amazon and leaders of San Francisco-Marin Food Bank highlighted their partnership that uses the company’s delivery network to bring food to community members who can’t get to a pantry. The company said Tuesday it has delivered more than 60 million meals for free from food banks across the US and UK, committing to continue the program through 2028.

A New York Times report on Tuesday, citing internal Amazon documents, said the company wants to automate 75% of its operations in the coming years to be able to avoid hiring hundreds of thousands of workers. It noted that the company is looking at burnishing its image through community programs to counteract the long-term fallout.

Executives noted that Amazon has focused in the Seattle region on affordable housing, in line with its approach of adapting to different needs in communities where it operates.

Lurie pointed to the company’s San Francisco food bank partnership as a model for other companies. “Amazon is showing that they are committed to San Francisco,” he said.

Microsoft CEO Satya Nadella’s total 2025 compensation rose nearly 22% from $79.1 million to almost $96.5 million, due mostly to the company’s booming share price boosting the value of his stock awards.

The numbers were disclosed Tuesday afternoon in the company’s annual proxy statement, along with details on Microsoft board changes, shareholder proposals raising concerns about AI risks, and a request from the board for shareholders to approve a new stock plan.

Microsoft laid off more than 15,000 employees this year — one of the most aggressive rounds of cuts in its history — citing shifting priorities and the need for efficiency amid record spending on AI infrastructure. Wall Street reacted positively to the effort to rein in operating expenses.

Much of Nadella’s total compensation — about $84.2 million — is based on the performance of the company’s stock, which has risen more than 23% in the past year, at one point pushing Microsoft’s total market value briefly past $4 trillion. 

Also announced in the proxy: Microsoft’s board nominated Walmart CFO John David Rainey as a new board member, to replace Carlos Rodriguez, current chair of the compensation committee, who is not seeking re-election.

The company’s 2025 fiscal year ended June 30. In evaluating Nadella’s performance, the board cited his work leading the expansion of the company’s AI infrastructure, Microsoft Copilot adoption and new security initiatives. 

His cash incentive bonus was $9.56 million, up from the $5.2 million paid in 2024, after he requested a reduction. The proxy statement said the increase reflected strong financial results (117% of target) and a high operational assessment (151.67% of target).

For the first time, security was used as one measuring stick for Microsoft executive compensation, part of an effort by the company to appease regulators and lawmakers after a series of high-profile breaches. In its review, the board focused on Nadella’s role in attempting to address these issues through the implementation of its Secure Future Initiative. 

In addition, Microsoft’s board is asking shareholders to approve a 2026 Stock Plan to replace the expiring 2017 plan, requesting authorization for up to 226 million new shares that it says is needed to continue granting equity awards for attracting and retaining talent.

Nadella recently appointed veteran executive Judson Althoff as CEO of Microsoft’s commercial business, a move designed to free Nadella to focus more intensely on long-term AI strategy and technology.

Microsoft’s annual meeting, held virtually, is slated for 8:30 a.m. Dec. 5.

A new Seattle startup is betting that artificial intelligence can take marketing off the plate of small business owners.

Omada.ai, founded earlier this year by longtime tech entrepreneur Pete Christothoulou, officially launched Tuesday with what it describes as an “AI marketing team” designed to handle the day-to-day digital marketing tasks for small and midsize business owners.

Backed by Crosslink Capital, HubSpot Ventures, and Seattle-based firm Ascend, the startup says its platform can plan, create, and optimize marketing campaigns automatically for less than $9 per day.

Instead of developing a single marketing “copilot” or dashboard, Omada’s approach is a set of coordinated AI agents — a marketing assistant, social media manager, designer, video producer, and more — that collaborate like a virtual team. Users interact through a simple chat interface, and the system handles tasks such as posting content, running ads, responding to customers, and tracking performance.

“Their agent-based architecture delivers a truly autonomous and proactive system that gives small business owners the access to capabilities and marketing expertise they’ve never had access to before,” Adam Coccari, managing director at HubSpot Ventures, said in a statement.

Omada’s pitch is that it acts less like another app and more like a full-service team — a “do-it-for-me” model rather than “do-it-yourself.” Its agents are built on proprietary infrastructure that coordinates specialized AI models for language, vision, and audio tasks. The company says the system learns each business’s tone and goals over time, continuously optimizing campaigns.

Omada enters an increasingly competitive space. A growing number of startups use generative AI to help businesses create content and automate tasks — including Seattle-area companies Gradial, Adora, and Forum3. Larger companies such as HubSpot, Canva, and Adobe have also embedded AI marketing tools into their small business offerings.

Christothoulou co-founded Omada with Siva Muthukumarasamy, a longtime engineering leader who was CTO at Peel Technologies, as well as Andrew Miller, a veteran marketing exec who worked at Xembly as head of user acquisition.

Omada marks Christothoulou’s latest foray into applying automation and data intelligence to the marketing world. He previously co-founded and ran Marchex, a Seattle-based advertising analytics company that went public in 2004 and helped pioneer digital call tracking for marketers.

Christothoulou served as CEO at Marchex until 2016 and later launched Xembly, a Seattle startup that developed an “AI chief of staff” to automate productivity tasks. The company shut down its consumer service last year.

Nine years ago, Clara Sekowski was part of the engineering team at Planetary Resources, a Seattle-area startup that planned to mine precious metals on asteroids. Six years ago, she joined other veterans from Planetary Resources at First Mode, another trailblazing startup that focused on clean energy for industrial applications. Now she’s the CEO of Special Teams, a consulting firm founded with fellow engineers from First Mode.

“Third time’s the charm, right?” she says.

Both of those earlier startups attracted high-profile backers for their ambitious plans, only to face setbacks as reality set in. Special Teams is starting smaller, but it’s gaining traction: The bootstrapped venture and its team of just over 10 engineers recently moved into a 7,400-square-foot office and workshop facility in Seattle’s SoDo neighborhood — and it’s already exceeding its revenue target.

“In our first year, we’re almost at $2 million, which is above and beyond a goal we had set for Year One,” she told GeekWire.

The Special Teams roster includes engineers with experience in aerospace, software development, and even the gaming industry.

“We use systems engineering to bridge the gap between innovation on paper and operational deployment,” Sekowski said. “We design and build prototypes and custom simulations to prove that concepts can work in real-world conditions.”

Special Teams’ to-do list includes helping BHP lay the groundwork for deep-mining automation; working on a confidential nuclear project; and advising Scuderia Cameron Glickenhaus, a high-performance car company, on its plan to create a hydrogen-powered pickup truck.

“I have worked for decades with top engineering and design companies around the world … on highly complex and challenging projects,” Jesse Glickenhaus, Scuderia Cameron Glickenhaus’ CEO, said in an emailed statement. “SpecTeams is by far the most incredible team I have worked with when doing something new and technologically challenging needs to be paired with significant safety and environmental concerns.”

Special Teams’ tangled origins

Sekowski and her teammates have had to deal with their share of technological challenges over the past decade. Redmond, Wash.-based Planetary Resources initially planned to build a fleet of spacecraft to seek out and mine asteroids, and then widened its focus to include Earth observation as well. But funding eventually ran out, and by the end of 2018, Planetary Resources was history.

Some of the engineers who left Planetary Resources started up First Mode. Initially, the engineering consulting firm played a supporting role in a variety of space projects, including NASA’s Artemis moon program and the Perseverance rover mission on Mars.

As time went on, First Mode tightened its focus to concentrate on clean-tech power systems. It established a proving ground for those systems at a former coal mine in Centralia, Wash. Then, in 2023, the Anglo American mining conglomerate took a majority interest in First Mode and accelerated its drive to develop hydrogen-fueled and hybrid powertrains for heavy trucks.

Last year, First Mode opened a 40,000-square-foot factory in the SoDo district — but the company also had to trim back its workforce to adjust to the market demand for clean tech. Months after the factory opened, Anglo American cut off funding for First Mode, setting the stage for a bankruptcy filing and an asset acquisition deal with Cummins, an Indiana-based power solutions company.

Molly Puga, First Mode’s general manager, said the company is continuing to pursue its decarbonization mission as part of the Cummins Power Systems global network.

“Since the acquisition of First Mode, Cummins has been hard at work bringing hybrid solutions for mining to reality,” Puga said in an emailed statement. “We have announced a partnership with Komatsu to scale our hybrid solution, received a grant from TransAlta to support operations at our proving grounds in Centralia, and have shipped product to South America to be commissioned at a mine in the next several months. First Mode continues to employ about 70 employees globally, with the majority of them based in Seattle.”

Special Teams has also been hard at work at its new SoDo facility.

“We are excited to be in the space that we have. It’s a great mix of space where we can build hardware and have a forklift and move around and make noise, and office space where we can get the rest of our work done,” Sekowski said. “SoDo is a great spot for that, because this is really the only area where you can have hybrid spaces. We are going to be here until our hardware doesn’t fit in the building anymore.”

Startups sparked, lessons learned

Special Teams isn’t the only startup founded by First Mode alumni: Last year, former CEO Chris Voorhees and former chief operating officer Rhae Adams established a think tank called Sol Zero Group to support new engineering ventures — including Special Teams.

Civic Forge, which advises businesses on government affairs and public policy strategies, is another venture in Sol Zero’s family of companies. It was founded last year by Conor Duggan, First Mode’s former director of government affairs; and Adam Day, who previously served as First Mode’s senior government affairs manager.

This year, Duggan took on a new role at a clean-tech startup called Vaulted Deep, and Day took charge as Civic Forge’s CEO.

“Civic Forge works alongside Special Teams when a challenge has both policy and technical dimensions,” Day told GeekWire via email. “Together, we pair engineering with policy, which helps clients de-risk designs, win public support and hit milestones faster. Our combined goal is simple: Help organizations move faster across dimensions so they can focus on building.”

Sekowski said that she gets “so much joy” from seeing former colleagues do well, at First Mode and at new ventures. “I think that’s part of the legacy,” she said. “It’s not just Special Teams, but it’s all of us, taking what we learned there and putting it into the next things that we do.”

She’s grateful for the experience she gained at First Mode. “Some of the things I learned at First Mode are important to us here as well,” she said. “Doing work in a broad domain, not just in space, but across energy and other industries, helps us do better work. And so that’s something that we’ll continue.”

Sekowski is even grateful for the setbacks she and her teammates encountered along the way. “I learned so much through the process of being a part of Planetary Resources, and then what was a strong correction to some of the funding issues there with First Mode, and now getting to put some of those lessons together to build this team,” she said. “You don’t get a lot of chances to grow in that way. … We’ve got the battle scars. We know where we want to go, what we don’t want to do, and how to get there.”

Amazon’s e-commerce customers are experiencing unusual delivery delays following the Amazon Web Services outage on Monday — suggesting that the cloud glitch has impacted the company’s own operations more than previously reported.

Customers posting on Reddit and X reported Amazon orders that were scheduled for Monday delivery but did not arrive. Some of the comments:

• “I received a delay email on everything due today. Coming tomorrow and I’m fine with that.”
• “I have 4 items that are suppose to be delivered today as well and they haven’t even left the facility. So I’m sure it’s the outage.”
• “My amazon fresh order was cancelled at 5:15PM.”

Amazon workers posting on the “r/AmazonFC” Reddit community cited downtime at fulfillment centers.

• “Today was the first day I’ve experienced an entire day of downtime, and not as a shutdown for maintenance. Very odd feeling to maintain a constant state of readiness for 10 hours in case the system comes back at any moment.”

We reached out to Amazon for details about delayed deliveries.

Amazon’s package fulfillment systems run atop AWS infrastructure — so disruptions in key AWS services can ripple directly into its retail and logistics network.

Amazon’s logistics arm processes about 17.2 million delivery orders per day, according to Capital One.

The fallout from delayed deliveries could lead to increased costs due to potential refund obligations and additional labor needs.

The outage started shortly after midnight Monday and lasted for about three hours, but the aftershock effects were felt by Amazon’s cloud customers for much of the day. The company blamed a DNS resolution issue with its DynamoDB service in US-EAST-1 region, it oldest and largest digital hub. Major outages originating from this same region also caused widespread disruptions in 2017, 2021, and 2023.

The outage impacted everything from sites including Facebook, Coinbase, and Ticketmaster, to check-in kiosks at LaGuardia Airport. Amazon’s own retail site, its Prime Video streaming service, and its Ring subsidiary were also affected.

Despite the major outage, Amazon’s stock was up Monday and in early Tuesday trading.

Veeam Software, the data backup and recovery company that recently moved its headquarters to the Seattle area, announced plans to acquire Securiti AI for $1.725 billion.

Securiti AI, based in San Jose, Calif., helps enterprises manage data security posture, privacy, and compliance across cloud and software platforms. The deal aims to integrate Securiti’s Data Security Posture Management (DSPM) and “AI trust” technologies with Veeam’s core data resilience tools, giving companies a single platform to manage, secure, and recover their data while safely deploying artificial intelligence systems.

“We’ve entered a new era for data. It’s no longer about just protecting data from cyber threats and unforeseen disasters; it’s also about identifying all your data, ensuring it’s governed and trusted to power AI transparently,” Veeam CEO Anand Eswaran said in a statement.

Rehan Jalil, Securiti’s CEO and a cybersecurity entrepreneur, will join Veeam as president of security and AI once the deal closes, expected in the fourth quarter.

Securiti, founded in 2019, raised a $75 million Series C round in 2022.

Veeam, which reached a $15 billion valuation earlier this year, relocated its headquarters from Columbus, Ohio, to the Seattle area in 2024, citing the region’s deep technical talent pool. The company employs about 6,000 people globally and protects data for more than 550,000 customers, including two-thirds of the Global 2000.

Veeam moved its headquarters from Switzerland to the U.S. following its March 2020 acquisition by private equity firm Insight Partners — a deal that valued the company at $5 billion at the time.

Veeam CEO Anand Eswaran, who joined the company in December 2021, previously worked in the Seattle area as the corporate vice president of Microsoft Enterprise. He was most recently president at RingCentral.

The effects of the massive AWS outage reached the sports world on Monday.

Ticketmaster was dealing with ticket management issues as a result of the outage, according to messages shared by several sports teams hosting games on Monday, including the Toronto Blue Jays and Seattle Seahawks.

The Blue Jays, facing off against the Seattle Mariners in a Game 7 MLB playoff bout at Rogers Centre in Toronto, posted a statement earlier Monday about the outage and advised fans to “hold off on managing your tickets as we work through this.”

A few hours later, the team said ticket management was returning to normal.

>World Series appearance on the line
>AWS outage sends Ticketmaster down
>Blue Jays fans can't access Game 7 tickets
>Blue Jays opponent…Seattle
>Amazon headquarters…Seattle https://t.co/OYjjDj5cdf pic.twitter.com/rbNnwKYegG

— Morning Brew ☕️ (@MorningBrew) October 20, 2025

The Seahawks, which are hosting the Houston Texans for Monday Night Football in Seattle, issued a statement about the outage “that may impact access to Ticketmaster, Seahawks Account Manager, and the Seahawks Mobile App.”

The Detroit Lions, hosting their own Monday Night Football game, also had ticketing impacted.

The outage effects went beyond just ticketing. The Premier League said its VAR tech system, used to determine offside calls in soccer, would not be available for Monday’s match between West Ham and Brentford.

Amazon’s outage began shortly after midnight Pacific in Amazon’s Northern Virginia (US-EAST-1) region, which is AWS’s oldest and largest cloud region, a popular nerve center for online services.

In an initial update, AWS said the outage was related to a DNS resolution issue with its DynamoDB product, meaning the internet’s phone book failed to find the correct address for a database service used by thousands of apps to store and find data.

Amazon later said the root cause of the outage was an “underlying internal subsystem responsible for monitoring the health of our network load balancers.”

By 3 p.m. PT, the company said all AWS services had returned to normal operations.

Major sites and services including Facebook, Snapchat, Coinbase and Amazon itself were impacted — reviving concerns about the internet’s heavy reliance on the cloud giant.

The outage suggests that many sites have not adequately implemented the redundancy needed to quickly fall back to other regions or cloud providers in the event of AWS outages.

Previously:

• AWS outage was not due to a cyberattack — but shows potential for ‘far worse’ damage
• AWS outage hits major apps and services, resurfacing old questions about cloud redundancy