Talk
Discover how BLACKBOX AI moved to Vercel to build a faster, more cost-efficient, and secure foundation for agentic AI. We’ll explore what drove the migration, how the team approached the technical journey, and how Vercel’s AI infrastructure supports open-source inference, end-to-end encryption, and enterprise-scale traffic without compromising performance.
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.
Talk
How do you serve 168 models through one integration and stay reliable at 3M+ requests a day? Adapta, the team behind Brazil's largest generative AI platform, did exactly that on AI Gateway and the Vercel Platform. Hear how they built an app-level router that picks the right model per request in under 200ms, wired up automatic failover and per-user budgets, and kept reliability climbing as traffic spiked. A practical look at the architecture decisions behind running frontier models at scale.
Panel
What changes when intelligence becomes fast enough to sit inside an everyday interaction? Join Vercel, TypeSafe AI, and Cerebras for a conversation about inference speed, model behavior, and the experience of building responsive AI applications. The panel brings application infrastructure, model development, and compute into the same discussion.
Talk
Learn how SpaceXAI's `.grok.me` surface runs 300k+ subdomains and 125M monthly Edge Requests on Vercel. Understand the infrastructure powering Grok and, most importantly, use Grok to ship.
Demo
Learn how Exa trains retrieval models that search across a live index of 100B+ embedded documents in milliseconds, and how to bring these capabilities to any domain-specific agent. Agents need specialized knowledge for coding, sales, marketing, legal, finance, recruiting, science, and personal assistance. In this talk, we'll build a context-rich agent using Exa + Vercel Eve and show context engineering strategies to adapt it to any use case.
