Notion Workers let you write and deploy code to give Custom Agents new powers: sync external data, trigger automations, call any API. With Workers, developers can build agents that sync CRM data on a schedule, open issues when error rates spike, and turn Slack threads into formatted content. Under the hood, every Worker runs on Vercel Sandbox. The problem: safely running code from any developer or agent Notion wanted to let anyone extend their platform with custom code. That's a hard infrastructure problem, but an even bigger security problem. Every Notion Worker runs arbitrary code generated by a third-party developer or agent, on behalf of a Notion user, potentially inside an enterprise workspace. Without proper isolation, a Worker would run in the same environment as the Custom Agent, with access to its secrets, permissions, and everything else in that execution context. A single prompt injection could exfiltrate credentials or access another user's data. The requirements were clear: Hard isolation: One Notion Worker can never access another's data or state Credential security: Notion Workers need API keys to talk to external services, but those secrets can never be exposed to the code itself Network controls: Enterprise customers need guarantees about the external services a Worker is allowed to reach Scale: Workers need to support millions of users running concurrent executions without performance degradation State preservation: Workers need fast cold starts, which require the ability to snapshot and restore filesystem state Economics: A billing model that is built for agents with low CPU utilization rates Why Vercel Sandbox Vercel Sandbox runs each Notion Worker in an ephemeral Firecracker microVM. Every VM boots its own kernel, providing stronger isolation than containers. Each execution gets its own filesystem, its own network stack, and its own security boundary. When the Notion Worker finishes, the microVM is either destroyed or snapshotted for later retrieval. To support workloads like Notion Workers at scale, Vercel Sandbox provides several critical capabilities: Credential injection. Sandbox's firewall proxy can intercept and inject API keys into outbound requests at the network level, so credentials never enter the execution environment. For agent-driven workloads, this eliminates the most dangerous prompt injection vector: an agent being tricked into exfiltrating secrets. (We wrote about this architecture in depth in security boundaries in agentic architectures). Network policies. Sandbox supports dynamic network policies that can be updated during runtime without restarting the process: start with internet access to install dependencies, then lock down egress before running untrusted code. Platform builders can pass these controls through to their own customers. Snapshots. Install dependencies once, snapshot the filesystem state, and resume from that snapshot on subsequent invocations. Combined with active-CPU billing, where CPU costs only accrue when your code is actually executing, not waiting on I/O, this keeps costs predictable as usage scales. The bigger picture: Notion as a developer platform Notion Workers isn't a one-off feature. It's the beginning of Notion becoming a developer platform. This shift requires infrastructure that Notion shouldn't have to build. Secure code execution, credential management, network isolation, file-sytem based snapshotting: these are hard problems that compound as the platform scales. Vercel Sandbox handles the infrastructure complexity so Notion can focus on the developer experience. What developers are building with Notion Workers Notion Workers support three main patterns: third-party data syncing, custom automations, and AI agent tools. Developers use them to sync external data, such as CRM records, analytics, and support tickets, into Notion on a schedule. A Worker can also be attached to a button, triggering arbitrary code with a single click. And when Notion's custom agents invoke Workers as tool calls, they become far more capable than agents limited to pre-built integrations. Extend your platform with Vercel Sandbox Notion Workers requires the same capabilities as other agent platforms. Any platform that wants to let users or agents run custom code faces the same set of problems: isolation, credential security, network controls, and scale. Vercel Sandbox provides these as capabilities out of the box. If you're building a platform that needs to run untrusted code, whether for AI agents, developer plugins, or workflow automation, then this is how you do it.

Gamma began with a simple idea: what if your presentation could design itself? With a single sentence, users can generate a complete presentation that respects layout, spacing, and hierarchy. Columns reflow automatically. Diagrams adjust when new layers are added. The product handles the formatting so teams can stay focused on the ideas. That philosophy reflects the company's DNA. Of Gamma's first ten hires, three were designers. "The attention to detail and value placed on design has been baked into the culture from the very, very beginning," says Sherwin Yu, Head of AI and Product Engineering. "Our designers at Gamma are fantastic. They ship code, they're technical. They'll push to production." "There's a lot of discussion about how do we, whenever possible, elevate the user experience," Sherwin says. As adoption grew, the team realized generation was only the beginning. Real presentation work happens in iteration. Teams outline, restructure, refine tone, and polish visuals. In October 2025, Gamma launched Gamma Agent, a conversational editing that shifted the AI capabilities dramatically. Evolving complex agent architectures with AI SDK The first version of Gamma generated decks from a prompt. Gamma Agent introduced dialogue, and with it, a new relationship between the user and the product. As the team started prototyping more powerful agents, that simplicity broke down. They needed finer control and more persistence over conversation state. They needed the ability to pass context from one agent to another, manage message history across sessions, and orchestrate more complex multi-step interactions than a simple request-response loop. The decisions a user made early in a workflow, the reasoning behind the structure, the tone they'd settled on… all of that was valuable context that couldn't just live in a disposable chat window. By building on the AI SDK rather than custom orchestration code, Gamma can evolve agent behavior without re-architecting its backend. Gamma's investment in composable, model-agnostic architecture extends beyond text. The company's image pipeline, which has generated more than 1.5 billion images across 60 models and 20 providers, has gone through its own architectural reckoning. Image generation Staying on the frontier of image generation means integrating new models fast… sometimes within days of launch. When the Vercel AI SDK introduced ImageModelV3, a standard interface for image generation with a composable middleware layer, Gamma's team saw it as yet another opportunity. Today, adding a new image model to Gamma is about 30 lines of code: just a model ID, cost formula, supported sizes, and capability flags. Tracing, cost tracking, and image preprocessing are handled automatically by shared middleware that wraps every model. Engineers never think about that plumbing; they just declare what a model can do. This pays off in the product. Infographics When the team shipped AI infographics, Gemini needed multimodal style references (actual images showing the target aesthetic), while Flux worked best with concise, text-only prompts. Because the model layer is just configuration, those per-model strategies live in the feature code, not buried in infrastructure. New model, new capability, new feature—each independent. The result: Gamma ships new models in hours, not weeks, and every model automatically gets production-grade observability from its first request. Shipping continuously with preview deployments Gamma applies the same philosophy to its deployment workflow: pick stable foundations, then move fast on top of them. Instead of building its own release system, the team relies on Vercel's Preview Deployments, production deployments, and Instant Rollbacks. "We try not to reinvent infrastructure we don't have to," Sherwin says. "We'd rather spend that engineering energy on the product." Despite Gamma’s team of just 20 or so engineers, Gamma averages more than 250 deployments per day across preview and production. Deploys complete in just over 7 minutes at median, with a 99 percent success rate. Preview deployments make it safe to experiment with agent behavior on every pull request. Instant Rollbacks provide confidence when shipping changes that affect model logic or orchestration. Scaling the AI content pipeline on Vercel Gamma's AI outputs raw HTML, but a presentation is more than markup, it's a structured document with layout rules, resolved images, live charts, and editable diagrams. Every generated card passes through a conversion layer that bridges that gap in real time. Gamma runs this critical translation layer as Vercel Functions. Every AI-generated card passes through a serverless endpoint that instantiates the complete Tiptap editor schema inside JSDOM, parses the LLM's HTML output into structured editor content, and resolves async assets. Other serverless functions handle the reverse direction (serializing editor content into AI-readable HTML) and generating theme preview images on the fly. All together, Gamma’s use of serverless functions ensures presentations load quickly and AI-powered editing stays responsive for users worldwide. Designing for what’s next As agents across the industry get more capable, the limiting factor shifts from intelligence to information. "An agent that knows your brand guidelines, your previous presentations, and your company's tone of voice is infinitely more valuable than a generic model," Sherwin says. "Right now, context is what separates a useful agent from a generic chat bot." He sees context operating at three levels: the immediate session, the user's history across projects, and the organizational layer (meaning things like brand assets, templates, knowledge base). Getting all three into the model's window, efficiently and at the right moment, is the architectural challenge every company building agents is wrestling with. It's the same vision Gamma has been building toward from day one, making it effortless to turn ideas into polished, compelling communication. First through intelligent layout and design. Then through conversational editing. And now, through a context layer that understands what you're building and why. What hasn't changed is how Gamma builds: pick the right abstractions, stay model-agnostic, keep enough flexibility to rebuild when the landscape moves, and ship before the window closes. In a space that reinvents itself every six months, that adaptability is the real moat.

Avalara connects businesses to more than 1,400 systems to automate tax compliance around the world. It’s a massively complex ecosystem that spans ERP systems, finance platforms, and compliance tools, all talking to each other. For Chief Strategy and Product Officer Jayme Fishman, the path forward is modernizing how Avalara builds. His mandate is to drive digital transformation, with a sharp focus on AI and innovation. Enter Vercel’s v0, which translates plain language into working prototypes. Within months, the team built two new patent pending products—and along the way, changed how the company builds. Seeing is believing Before v0, bringing an idea to life required a mountain of slides, careful specs, and ample interpretation. Fishman might have a strong vision, but getting started meant writing everything down, then waiting for designers and engineers to bring it to life.  “It could be a significant delay before we even had a conceptual mock-up.” That changed overnight. One of Avalara's biggest challenges was supporting customers who could be plugging into more than a thousand different systems. "We could provide technical documentation and show customers what to do," Fishman said, "but we couldn't see what they were doing. Once they left our system, we lost visibility… and the ability to help." Fishman imagined a solution that could meet customers where they were. What if Avalara built a Chrome extension that could live alongside a user's workflow, walk them through each step of an integration specific to the systems they were using, and stay behind to answer any questions? He described it to a teammate, who went straight into v0. "The next morning, there's a video in my Slack. It shows exactly what I described the night before," Fishman recalled. "I showed it to my exec team, and all the light bulbs lit up." “I can describe what I want and wake up to a working demo. It’s tectonically shifting how we build.” That demo—built in v0—became the basis for a new patent, a production build, and a press release, all within about 60 days. “It was one of those moments,” he said, “where you realize you don’t need to talk people into an idea if they can see it.” Driving alignment with product design Like many SaaS organizations, Avalara’s product and design process used to depend on long handoffs. Product managers wrote PRDs. Designers translated them into Figma files. Engineers reviewed and rebuilt. “There’s desire and intent,” Fishman said, “and then there’s what actually happens—where everyone gets tagged in late and we lose momentum.” With v0, that flow changed completely. Product leads now start directly in the tool, describing what they want in plain language and watching v0 translate intent into a functioning interface. “It’s like you can will it into existence,” Fishman said. “You describe the problem, and five minutes later, you’re looking at a solution.” For designers, the shift has been equally dramatic. “You can just grab someone, show them what you mean, and start iterating,” Fishman explained. “It takes something that used to be async and turns it into a real conversation.” A new way of building Across Avalara, prototypes have replaced concepts. Fishman calls it “a cultural accelerant.” The results speak for themselves: two patent-pending products created in roughly 60 days, faster design and validation cycles, and a company-wide shift toward building through iteration, not interpretation.” About Avalara: Avalara connects businesses to more than 1,400 systems to automate tax compliance around the world.

Andy Yoon was scrolling through Slack when he saw the message: OpenEvidence had gone viral on TikTok. Not "gaining traction.” Actually viral, reaching around two million views in less than a week.  This is usually when you rally the troops, spin up emergency capacity, and start making phone calls you really didn't want to make. Andy, Lead Frontend Engineer, did none of those things. Instead, he watched the numbers climb. He checked the logs—everything green. Response times: still fast. Error rates: still near zero. Then he went back to whatever he was doing before, because there was nothing to fix. "Vercel has just completely scaled with that usage," he says. "We've never had it fall over due to capacity or had to provision anything extra. Just being able to trust that it's there, to the point where we don't really even think about it, is amazing." It was proof that they'd solved a problem most healthcare tech companies haven't figured out yet: how to move at startup speed while meeting hospital-grade reliability standards. When failure isn't an option The stakes are different for companies like OpenEvidence. If their product fails, it could result in someone making a bad medical decision.  OpenEvidence is the most widely used clinical decision support platform among U.S. clinicians, supporting over 20 million clinical consultations in January 2026. Over 100 million Americans were treated by a doctor using OpenEvidence last year. A general-purpose model can afford to be wrong, but a clinical tool cannot. Physicians expect speed, but they also expect stability, clarity, and trust. This pressure sits on top of every technical decision at OpenEvidence: it has to work, every time. A frontend engineer and a team of Python developers When Andy joined OpenEvidence about three years ago, he discovered something that would make most frontend engineers nervous: he was basically the only one. "I was pretty much the only engineer on our team coming from an actual frontend background," he says. "Most of our team works in Python and machine learning." They couldn't afford infrastructure that needed constant babysitting. They needed something that would just work. Deploy code, it goes live. Traffic increases, it scales. So OpenEvidence uses a hybrid architecture. The backend is built in Python and runs on Google Cloud Platform. It handles data ingestion, model orchestration, and core business logic, while the frontend is built with Next.js and deployed on ‌Vercel. ‌‌ "Given the makeup of our engineering team, Vercel has really scaled with our frontend so well," Andy notes.  Each commit deploys automatically. Production deploys take five minutes. Preview URLs appear for every branch. For a small team supporting millions of medical consultations daily for almost half of all physicians in the US, it’s been indispensable. Prototyping at speed Before OpenEvidence became what it is today, it was dozens of other things first. Each proof of concept was deployed on Vercel as its own project with a custom domain.  Vercel made it simple. Spin up a new project, connect a custom domain, push code, and you have what looks like a production environment. Stakeholders could click around and test workflows. This ability to spin up projects in minutes helped the team find product-market fit. It also made it easier to win early enterprise partnerships. When building out new features, preview deployments give them shareable links for live demos. Changes can be rolled out safely, because they can be reverted instantly if needed. The 90% surprise As OpenEvidence scaled to 1000x growth, the lead infrastructure engineer, Micah Smith, kept a close eye on compute costs. When Vercel introduced Fluid compute, it changed how serverless workloads run—combining on-demand execution with server-like efficiency, lower latency, and better performance under load. The team enabled Fluid compute to see what would happen, and their serverless spend dropped by 90%. Same reliability. Faster speed. Fewer cold starts.  "We reduced our serverless spend by 90% while maintaining the same performance, and even as we've scaled up to 1000x growth, Vercel is less than 5% of our overall infra spend." —Micah Smith, VP Engineering The infrastructure is almost invisible, meaning more time spent on product experience and less time debugging tools or provisioning servers. Threading the needle "A lot of doctors and medical professionals are used to really outdated software," Andy says. He's not wrong. Hospital software often looks like it was designed in the '90s, but those tools are reliable. OpenEvidence has to thread the needle, building a modern solution that upholds the reliability bar.  Their viral moment proved the platform could handle a sudden influx while maintaining hospital-grade reliability. It did. Since launching, OpenEvidence has grown to serve over 40% of physicians in the United States. The frontend team is still small. The infrastructure still just works. About OpenEvidence: OpenEvidence is the fastest-growing clinical decision support platform in the United States, and the most widely used medical search engine among U.S. clinicians. OpenEvidence is trusted by hundreds of thousands of verified healthcare professionals to make high-stakes clinical decisions at the point of care that are sourced, cited, and grounded in peer-reviewed medical literature. Founded with the mission to help doctors save lives and improve patient care, OpenEvidence is actively used daily, on average, by over 40% of physicians in the United States, spanning more than 10,000 hospitals and medical centers nationwide. Learn more at openevidence.com.

How the 6-person team at Stably ships AI testing agents faster with Vercel—moving from weeks to hours. Their shift highlights how Vercel's platform eliminates infrastructure anxiety, boosting autonomous testing and enabling quick enterprise growth. Jinjing Liang, co-founder and CEO of Stably, was building something technically ambitious: AI agents that run autonomous end-to-end tests by deploying on preview URLs, reading code diffs, and validating whether changes actually work. Testing is the bottleneck for autonomous coding: AI can write code fast, but without validation, teams get stuck checking everything manually. But Stably had their own bottleneck. Every new feature meant infrastructure decisions. Every new agent meant deployment anx...

What would traditionally require months of product-development coordination and building across multiple teams was achieved by one person in a single flight. Inside Stripe’s push to make value tooling faster, smarter, and fully self-serve for their GTM teams Mario Braz boarded an international flight with a problem. He deplaned with a working production application. With a finance background and zero formal engineering training, Mario Braz, Stripe GTM Business Value Consulting, used v0 to prototype a full application during a long-haul flight. By the time he landed, the first version was working, fully web-based, mobile-friendly, and ready to deploy....

Sensay went from zero to an MVP launch in six weeks by leaning on Vercel previews, feature flags, and instant rollbacks. The team kept one codebase, moved fast through pivots, and shipped without a DevOps team. Impact at a glance 6 weeks from zero to MVP launch for Web Summit Zero upfront infrastructure cost to go live No DevOps team required Fast iteration loops using preview deployments and feature flags A startup searching for its market Sensay did not start as an employee off-boarding platform. The company's original mission was deeply human: build "replicas" of people that could capture their knowledge, voice, and image so families could preserve memories before cognitive decline set in. The team ...

Rox is building the next-generation revenue operating system. By deploying intelligent AI agents that can research, prospect, and engage on behalf of sellers, Rox helps enterprises manage and grow revenue faster. From day one, Rox has built their applications on Vercel. With Vercel's infrastructure powering their web applications, Rox ships faster, scales globally, and delivers consistently fast experiences to every customer.

Founded in 1877, Helly Hansen is a global leader in technical apparel, but its digital experience wasn't living up to its legacy. Operating across 38 global markets with multiple brands (including HellyHansen.com, HHWorkwear.com, and Musto.com), the company was being held back by an outdated tech stack that slowed site speeds and frustrated customers. Through an incremental migration to Next.js and Vercel, Helly Hansen improved Core Web Vitals from red to green, increased developer agility, and delivered a record-breaking Black Friday Cyber Monday, building a foundation for future innovation.

Code and Theory is a digital-first creative and technology agency that blends strategy, design, and engineering. With a team structure split evenly between creatives and engineers, the agency builds systems for global brands like Microsoft, Amazon, and NBC that span media, ecommerce, and enterprise tooling. With their focus on delivering expressive, scalable digital experiences, the team uses v0 to shorten the path from idea to working software.

Coxwave helps enterprises build GenAI products that work at scale. With their consulting arm, AX, and their analytics platform, Align, they support some of the world’s most technically sophisticated companies, including Anthropic, Meta, Microsoft, and PwC. Since the company’s founding in 2021, speed has been a defining trait. But speed doesn’t just mean fast models. For Coxwave, it means fast iteration, fast validation, and fast value delivery. To meet that bar, Coxwave reimagined their web app strategy with Next.js and Vercel.

Ready.net is a core platform that helps utility companies manage their financing and compliance, the company works with a wide network of state-level stakeholders. New feature requirements come in fast, often vague, and always critical. With limited design resources supporting three teams, the company needed a way to speed up the loop between ideation, validation, and delivery. That’s where v0 came in.