Vercel Ship 2026 recap

For a decade, Vercel has shaped how the web is built. Now, we’re doing the same for agents. The companies that win the next decade will build on infrastructure designed for agents from the start, and thousands of people gathered across London, Berlin, New York, Sydney, and San Francisco to do just that at Vercel Ship 2026.

Copy link to headingAgentic infrastructure

Guillermo Rauch (CEO, Vercel) opened Ship SF with a vision for the next era of software and agentic infrastructure: interfaces generated for any task in front of you, agents that reproduce and fix bugs autonomously, and software that takes production context and continuously improves itself.

Production context is what turns software into a loop, because what happens in production drives what gets built next.Guillermo Rauch Founder & CEO @ Vercel

Production context is what turns software into a loop, because what happens in production drives what gets built next.

Guillermo Rauch Founder & CEO @ Vercel

Agentic infrastructure has three parts:

• Vercel is where you build and deploy your own apps and agents. We give you every tool you need to build and run apps and agents in production, securely, at scale.

Vercel is where you build and deploy your own apps and agents. We give you every tool you need to build and run apps and agents in production, securely, at scale.

• Vercel is where coding agents deploy that software. When you ask your harness where to deploy, you get Vercel, because Vercel is built for the way agents work. We have over 200 CLI commands that your agent can use to operate our entire platform.

Vercel is where coding agents deploy that software. When you ask your harness where to deploy, you get Vercel, because Vercel is built for the way agents work. We have over 200 CLI commands that your agent can use to operate our entire platform.

• Vercel itself is automated by agents. Vercel runs your apps in production, handling traffic, traces, observability, and anomalies. That data gives our agents the context they need to investigate autonomously, and then surface pull requests, not just alerts.

Vercel itself is automated by agents. Vercel runs your apps in production, handling traffic, traces, observability, and anomalies. That data gives our agents the context they need to investigate autonomously, and then surface pull requests, not just alerts.

Copy link to headingAgentic Infrastructure is for developers

In his opening keynote, Guillermo pointed to claims that AI would replace developers, then used Vercel's own data to prove them wrong. In the last 12 months:

• The number of developers on Vercel has grown 3x

The number of developers on Vercel has grown 3x

• The number of new projects developers ship has doubled

The number of new projects developers ship has doubled

• The number of their agent-triggered deployments has increased 28x

The number of their agent-triggered deployments has increased 28x

"We built Vercel for developers," he said, "because they are the difference between a world full of slop and a world full of software worth using."

Copy link to headingBackends on Vercel

In the next keynote, Malte Ubl (CTO, Vercel) showed how frontends, APIs, backend services, containers, MCP servers, and background workers can all run on Vercel, with support for custom runtimes and system dependencies.

He then announced that Python is now generally available on Vercel. Run FastAPI, Flask, or Django with standard CPython, PyPI dependencies, uv, and pyproject.toml. With Vercel Services, your frontend and backend deploy together, with previews of the full app.

Malte also introduced Vercel Daemons, now in public beta, for continuously running background workers. Deploy your code or container image, set the number of instances, and Vercel keeps them running and replaces them if they fail. Bring Celery, Dramatiq, Temporal workers, or your existing worker processes.

Copy link to headingVercel is for shipping agents

Tomo Occhino (CPO, Vercel) walked through the Agent Stack and its latest updates. The Agent Stack gives you everything you need to build, run, and scale agents in production.

• Vercel Drives, now generally available for Sandbox, gives agents persistent workspaces. Code, data, and saved memory survive across runs, so you can change runtimes or compute without rebuilding the workspace.

Vercel Drives, now generally available for Sandbox, gives agents persistent workspaces. Code, data, and saved memory survive across runs, so you can change runtimes or compute without rebuilding the workspace.

• eve, our open-source framework for building agents, now has persistent memory across sessions, extensions for installing tools and skills, and agent creation and deployment from the Vercel dashboard.

eve, our open-source framework for building agents, now has persistent memory across sessions, extensions for installing tools and skills, and agent creation and deployment from the Vercel dashboard.

• Vercel Connect is generally available, with more than 1,000 connectors. And MCP Events, now in public beta, lets agents respond to events from MCP servers. Connect handles subscriptions, renewals, and secure delivery.

Vercel Connect is generally available, with more than 1,000 connectors. And MCP Events, now in public beta, lets agents respond to events from MCP servers. Connect handles subscriptions, renewals, and secure delivery.

• AI Gateway now lets you set budgets for API keys, projects, individuals, and teams. You can also choose US-only inference to keep model processing in the United States, or enable Zero Data Retention so providers don’t retain your prompts or responses. He also introduced Vercel Token Pass, now in early access for Pro teams. Get $80 in GLM 5.3 and Kimi K3 token credit for $30/month, with more models coming soon.

AI Gateway now lets you set budgets for API keys, projects, individuals, and teams. You can also choose US-only inference to keep model processing in the United States, or enable Zero Data Retention so providers don’t retain your prompts or responses. He also introduced Vercel Token Pass, now in early access for Pro teams. Get $80 in GLM 5.3 and Kimi K3 token credit for $30/month, with more models coming soon.

Copy link to headingVercel for enterprise

Jeanne Grosser (COO, Vercel) focused on what happens when everyone in a company can build. Engineers, marketers, analysts, and sellers need a common place to deploy, with controls over who can ship, who can access an app, which systems agents can use, and how much they can spend. Company building is now agent building.

Vercel for Enterprise brings those controls together, with two additions announced:

• Bring Your Own Cloud on AWS is now generally available. Your application functions run in your own AWS account, within your security and network boundaries.

Bring Your Own Cloud on AWS is now generally available. Your application functions run in your own AWS account, within your security and network boundaries.

• Enterprise-Managed Authorization for Vercel Connect launched in public beta. With supported services and your identity provider configured, agents can act on employees’ behalf without asking each person to authorize every connection separately.

Enterprise-Managed Authorization for Vercel Connect launched in public beta. With supported services and your identity provider configured, agents can act on employees’ behalf without asking each person to authorize every connection separately.

Copy link to headingShip week in San Francisco

The rest of Ship SF brought more than 2,700 developers, founders, and technical leaders to the Palace of Fine Arts for talks, workshops, startup studio sessions, and agent labs.

Copy link to headingShip day sessions

• Assaf Elovic from Ora showed how his team tests whether websites work for agents by sending real agents to sign up, integrate, and pay, then tracing every step. Ora built that fleet on eve and used Is-Agentic to score a live site.

Assaf Elovic from Ora showed how his team tests whether websites work for agents by sending real agents to sign up, integrate, and pay, then tracing every step. Ora built that fleet on eve and used Is-Agentic to score a live site.

• Katelyn Lesse from Anthropic covered the work that starts after an agent is running: keeping it fast and improving its performance across thousands of production sessions with Claude Managed Agents on Vercel.

Katelyn Lesse from Anthropic covered the work that starts after an agent is running: keeping it fast and improving its performance across thousands of production sessions with Claude Managed Agents on Vercel.

• Prashant Ratanchandanifrom Meta Superintelligence Labs joined Tomo to discuss building products including Muse on Vercel.

Prashant Ratanchandanifrom Meta Superintelligence Labs joined Tomo to discuss building products including Muse on Vercel.

• Matt Lewis from Vercel and Mala Neti from Slack explained how we built v, our internal agent, around Vercel’s own data and working practices. Connect and Passport secure its access, and Slack gives employees a place to use it where their work already happens.

Matt Lewis from Vercel and Mala Neti from Slack explained how we built v, our internal agent, around Vercel’s own data and working practices. Connect and Passport secure its access, and Slack gives employees a place to use it where their work already happens.

• Max Peters from Adapta broke down the router behind Brazil’s largest generative AI platform. Built on AI Gateway, it serves 168 models through one integration, selects a model in under 200 milliseconds, and handles more than three million requests a day with automatic failover and per-user budgets.

Max Peters from Adapta broke down the router behind Brazil’s largest generative AI platform. Built on AI Gateway, it serves 168 models through one integration, selects a model in under 200 milliseconds, and handles more than three million requests a day with automatic failover and per-user budgets.

• Sarah Sachs from Notion and Malte Ubl discussed how AI is changing the software teams build and the context agents need to do useful work.

Sarah Sachs from Notion and Malte Ubl discussed how AI is changing the software teams build and the context agents need to do useful work.

• Olawale Oladehin from AWS walked through production patterns for agents on AWS and Vercel, from self-correcting agents to multi-agent orchestration, and how BYOC lets teams run application functions within their own AWS environment.

Olawale Oladehin from AWS walked through production patterns for agents on AWS and Vercel, from self-correcting agents to multi-agent orchestration, and how BYOC lets teams run application functions within their own AWS environment.

• Philip Miseldine and Sophia Levens from SAP showed how SAP is using v0, eve, and json-render to build generative interfaces, with a focus on consistent design and government requirements.

Philip Miseldine and Sophia Levens from SAP showed how SAP is using v0, eve, and json-render to build generative interfaces, with a focus on consistent design and government requirements.

• Aaron Brown and Arty Vohmincevs from Mercor explained how hundreds of employees build internal tools without losing control of access or spending. Apps inherit a managed identity layer, while AI Gateway gives the team visibility into model usage and budgets.

Aaron Brown and Arty Vohmincevs from Mercor explained how hundreds of employees build internal tools without losing control of access or spending. Apps inherit a managed identity layer, while AI Gateway gives the team visibility into model usage and budgets.

• Yury Izrailevsky from ClickHouse traced the company’s path from an open-source analytics database to a platform spanning observability, AI engineering, and managed Postgres. His focus was how open source earns developer trust and helps infrastructure expand into new workloads.

Yury Izrailevsky from ClickHouse traced the company’s path from an open-source analytics database to a platform spanning observability, AI engineering, and managed Postgres. His focus was how open source earns developer trust and helps infrastructure expand into new workloads.

Copy link to headingPanel: Fast AI

Diogo Almeida, co-founder and CEO of TypeSafe AI, the company behind Jev, and Andrew Feldman, founder and CEO of Cerebras, joined Vercel for a discussion on model reliability, latency, and cost. The panel brought together the model and hardware sides of fast inference, from specialized models to wafer-scale chips.

Copy link to headingClosing fireside with Tobi Lütke

Guillermo sat down with Tobi Lütke, CEO of Shopify, for "The Third Customer," a conversation about building for a world where agents research, compare, and buy products on people’s behalf.

Guillermo Rauch: What excites you about agentic commerce?

Tobi Lütke: It’s early, but the opportunity goes beyond handling purchases people already make. Think about project-based commerce: planning Halloween decorations for your house, or a 3D-printing project with your kids, then ordering everything to arrive before the weekend. Agents can help people follow through on things they otherwise wouldn’t have had time to do.

Guillermo Rauch: Where does that leave traditional storefronts?

Tobi Lütke: There’s still room for exceptional shopping experiences. A distinctive, thoughtful storefront can grow, just as a well-executed boutique can. The businesses that will struggle are the ones offering an undifferentiated experience. Quality and originality still matter.

Guillermo Rauch: How is AI changing engineering at Shopify?

Tobi Lütke: We now think of ourselves as verification engineers, building harnesses and acceptance tests that make changes verifiable. We’re rewriting our storefront renderer from Ruby to Rust, where we can compare the output byte for byte before switching over. We also celebrate simplification and code deletion. At a company hackathon, our internal Slack agent, River, topped the code-deletion leaderboard by a wide margin.

Guillermo Rauch: What should developers in this room go build?

Tobi Lütke: Explore the catalog APIs. They give you access to products from Shopify merchants, so you can build new commerce experiences without first recruiting both sides of a marketplace. Product discovery, recommendations, and curation are real business opportunities. People will pay for tools that help them find what they need.

Copy link to headingShip week San Francisco

Copy link to headingFast Forward hackathon

The day before Ship, Vercel and Meta hosted Fast Forward, with support from Shopify and Neon Postgres. Builders worked across three tracks: agents that keep working after you step away, multimodal apps, and immersive VR experiences.

Copy link to headingFounder dinners, executive conversations, and Partner Day

Founders, partners, and enterprise leaders gathered throughout the week for dinners, Partner Day, and conversations on building with AI. The executive program focused on what happens when anyone with an idea can build, and how do you govern what ships.

Copy link to headingShip 2026 in London

Copy link to headingShip day keynotes

• Tomo introduced the Agent Stack, bringing model access, durable execution, sandboxed compute, and messaging together for production agents.

Tomo introduced the Agent Stack, bringing model access, durable execution, sandboxed compute, and messaging together for production agents.

• Hedi launched Vercel Connect in public preview, giving agents scoped access to external tools and data without storing long-lived provider credentials in environment variables.

Hedi launched Vercel Connect in public preview, giving agents scoped access to external tools and data without storing long-lived provider credentials in environment variables.

• Shar demoed eve, our open-source agent framework. Each agent lives in a directory, with instructions in Markdown and tools in TypeScript. Durable execution, approvals, subagents, and evals are already wired in.

Shar demoed eve, our open-source agent framework. Each agent lives in a directory, with instructions in Markdown and tools in TypeScript. Durable execution, approvals, subagents, and evals are already wired in.

• Jeanne introduced Vercel for Enterprise Apps and Agents, including Vercel Passport in public beta for protecting internal apps with your identity provider, and Bring Your Own Cloud on AWS in private beta.

Jeanne introduced Vercel for Enterprise Apps and Agents, including Vercel Passport in public beta for protecting internal apps with your identity provider, and Bring Your Own Cloud on AWS in private beta.

Copy link to headingShip week London

Our first Ship outside the U.S. ran five days of events leading into the keynote, and an ice cream truck spent the week working its way across the city.

Copy link to headingBuilt in London hackathon

Two hundred builders shipped agents on Codex and Vercel in a hackathon with OpenAI. Three projects stood out. Stella hunts down unclaimed grants for London SMBs, Oscar is a co-pilot that sharpens your prompts before you send them to a model, and Phone Jail blocks distractions and roasts you when you reach for your phone anyway.

Copy link to headingMedia, Founder, VC, and CTO dinners

Reporters traded story ideas over a media dinner. Twelve founders talked through the future of AI in EMEA at a VC dinner. And a dozen CTOs from teams including Marks & Spencer and Currys went off the record on what it takes to build and scale agents in the enterprise.

Copy link to headingDay Zero builder night

Day Zero, the day before the keynote, turned into a 400-person builder night. Enterprise teams Mentimeter, Okta, and MongoDB joined Vercel in a packed room alongside partners DeepMind, ElevenLabs, and Cursor.

Copy link to headingAI Social Club

A 160-deep waitlist formed for Malte's talk A New Stack for a New Era of Software, followed by Guillermo and Deliveroo's Will Shu's chat on building the agentic enterprise.

Copy link to headingShip day sessions

• André Balleyguierfrom Anthropic showed Claude Managed Agents on Vercel, where Anthropic hosts the agent loop while every command the agent runs executes inside a Vercel Sandbox you own, keeping its filesystem, processes, and network egress in your environment.

André Balleyguierfrom Anthropic showed Claude Managed Agents on Vercel, where Anthropic hosts the agent loop while every command the agent runs executes inside a Vercel Sandbox you own, keeping its filesystem, processes, and network egress in your environment.

• Tomas Janssonfrom Currys/Elkjøp showed how his team evolved a Nordic retailer's ecommerce stack from storefronts toward shopping agents in three phases, anchored by a Next.js migration that cut time to first byte by 40%. The end state is one where customer intent replaces navigation.

Tomas Janssonfrom Currys/Elkjøp showed how his team evolved a Nordic retailer's ecommerce stack from storefronts toward shopping agents in three phases, anchored by a Next.js migration that cut time to first byte by 40%. The end state is one where customer intent replaces navigation.

• Matan Kushner from Vercel broke down how Vertex, Vercel's support agent, now automates 91% of support tickets and saves 5,000 engineer-hours a month without degrading as its context grows.

Matan Kushner from Vercel broke down how Vertex, Vercel's support agent, now automates 91% of support tickets and saves 5,000 engineer-hours a month without degrading as its context grows.

• Jas Sagoo and Sam Bellen from Auth0 made the case that getting an agent into production depends more on identity than on model quality. They demoed four standards-based identity patterns on the Vercel AI SDK, Token Vault, CIBA approvals, agents as first-class principals, and on-behalf-of delegation, so every action is scoped and traces back to a human decision instead of a shared API key.

Jas Sagoo and Sam Bellen from Auth0 made the case that getting an agent into production depends more on identity than on model quality. They demoed four standards-based identity patterns on the Vercel AI SDK, Token Vault, CIBA approvals, agents as first-class principals, and on-behalf-of delegation, so every action is scoped and traces back to a human decision instead of a shared API key.

• Abhi Sivasailam from Vercel went deep into d0, Vercel's internal data agent built on eve, which runs analyses in a sandbox and now gets 45% of its questions from other agents, rather than people.

Abhi Sivasailam from Vercel went deep into d0, Vercel's internal data agent built on eve, which runs analyses in a sandbox and now gets 45% of its questions from other agents, rather than people.

• Romain Huet from OpenAI showed developers how to ship faster by delegating whole tasks to Codex Cloud Agents on Vercel, and made the case that as agents become users of your product, you design for agent experience with scoped API keys, markdown docs, and plugins.

Romain Huet from OpenAI showed developers how to ship faster by delegating whole tasks to Codex Cloud Agents on Vercel, and made the case that as agents become users of your product, you design for agent experience with scoped API keys, markdown docs, and plugins.

• Michał Pierzchała from Callstack demoed a QA agent that runs mobile apps on real devices, explores user flows on its own, and posts screenshots, recordings, and logs to pull requests on every PR.

Michał Pierzchała from Callstack demoed a QA agent that runs mobile apps on real devices, explores user flows on its own, and posts screenshots, recordings, and logs to pull requests on every PR.

• Alex Holt from ElevenLabs paired the ElevenLabs Speech Engine with the AI SDK to build a voice agent that can reply in under a second, take interruptions mid-sentence, and switch language mid-conversation.

Alex Holt from ElevenLabs paired the ElevenLabs Speech Engine with the AI SDK to build a voice agent that can reply in under a second, take interruptions mid-sentence, and switch language mid-conversation.

• Malavika Balachandran Tadeusz from Vercel showed the mechanics of how software can ship itself, extending the agent loop past development into testing, observability, and experimentation with primitives like Vercel Flags and Skills.

Malavika Balachandran Tadeusz from Vercel showed the mechanics of how software can ship itself, extending the agent loop past development into testing, observability, and experimentation with primitives like Vercel Flags and Skills.

Copy link to headingPanel: Agents in production

Jeanne Grosser, COO of Vercel, moderated a panel on taking agentic workloads from prototype to production with some of the EU's top CTOs and AI leaders from frontier labs. A few highlights:

Arthur Viegers (Cursor): Autonomy should track risk, and the better an agent can assess the risk of a change, the more you can let it run on its own. Shopify and Amplitude already auto-review and merge 60-70% of low-risk PRs with no developer time, while a two-line change to authentication still goes to a human.

André Balleyguier (Anthropic): To decide what an agent can do on its own, judge each action by how reversible it is and how large its blast radius is, then contain it accordingly, for example inside a self-hosted sandbox. As you grant more autonomy, observability and evals become the things that keep it safe.

Ryan den Rooijen (Currys): The predicted death of stores never arrived, and Currys leads its markets by betting on humans. The open question for agentic commerce is which shopping journeys customers want an agent to handle and which they still want a person for.

Nicolas Le Pallec (AKQA): AI-native customer experience replaces navigation with intent. Reaching it takes three layers: a way to capture true customer intent, a brand brain that stores brand and product data for AI systems to retrieve, and generative UI that composes pages on the fly instead of serving static ones.

Copy link to headingFireside chat with Harry Stebbings

The day ended with a fireside chat between Guillermo and Harry Stebbings from 20VC. Below are excerpts from the lightning round at the end of the discussion.

Copy link to headingShip 2026 in Berlin