Keynote
The final actor is shifting from human to machine. Software acts on behalf of users, writes itself, and needs to understand its own behavior in production. This new generation of agentic software demands Agentic Infrastructure.
Talk
Getting agents running is half the battle. Making them performant and continuously improving across thousands of sessions is much more challenging. This talk covers how to do it with Claude Managed Agents running on Vercel's agentic infrastructure, including best practices for optimizing agentic performance in production.
Demo
Companies use Ora to find out whether their website works for AI agents, and the way Ora answers is by sending real agents onto the site to sign up, integrate, and pay, then tracing every step. Hear how the Ora team built an agent fleet on eve, what hundreds of real agent journeys show about where websites break, and see Is-Agentic score a live site.
Fireside chat
Muse, the world's first personal AI agent built for everyone, runs on Vercel, alongside Meta AI and other Meta Superintelligence Labs projects. Hear how Meta and Vercel are building together at the frontier of AI, and take away lessons you can apply to your own projects tomorrow.
Talk
Last year was about Agents at Work.This year, we built our own.Meet V, Vercel’s super intelligent custom agent. See how we built it, what we learned, and how you can build your own.
Talk
How do you build in an AI-first world? Learn the agentic patterns shipping to production across hundreds of engineering teams, from self-correcting agents to multi-agent orchestration, built on AWS and Vercel. See how Vercel's BYOC on AWS delivers platform speed with full VPC control.
Fireside chat
People have long been the audience for the software we build. What happens when agents become customers too? Tobias Lütke and Guillermo Rauch discuss the implications for commerce, application design, and the relationship between developers and the users—human or machine—on the other side of an interface.
Workshop
Eve is Vercel's framework for durable backend agents, and it starts with a directory. In this hands-on session, you'll go from empty folder to running agent in under an hour: filesystem-first authoring, the channel/harness/workflow runtime, and shipping agents that survive restarts. No experience required.
Talk
Most agents handle one prompt and a quick burst of work. Hyperagent runs agents that wake on a schedule, work for hours in real browsers and code environments, and escalate to humans. Built on Vercel Sandbox with AI Gateway, we tested 14 models on 42 real jobs and found a 50x cost gap on identical tasks.
Workshop
Build an agent into a Next.js application that works with application data and generates interactive tools. This 40-minute workshop brings together Codex and Vercel Sandbox for a focused, end-to-end demonstration.
Talk
See how Notion uses Vercel's primitives to build a platform designed for both developers and AI agents.
Talk
Building a custom agents platform is one of the key pieces to unlocking AI for complex business workflows. Monte Carlo is the sales-specific system we've built to help scale Monaco's revenue: a platform where revenue teams encode their own playbooks as agents that run against everything we've ingested about their business, including pipeline, outbound, calls, and CRM. Sales is a particularly complex vertical for the following reasons: no two revenue orgs look alike, the data is large and heterogeneous, and the expertise that matters lives in per-rep workflows nobody has written down. Making it work at scale meant rebuilding the agent runtime on per-run Vercel Sandbox microVMs, a decision that propagated much further than we expected into how we handle context, how much of a playbook ends up as prose versus code, and what an agent is permitted to do at all. In this talk, I'll break down the components a verticalized agent platform needs in order to be fast and correct, including an execution substrate, memory and context, how expertise gets represented, and the evaluation loop, along with what is still unresolved.
