The Search Engine for the Agentic Web
Every search API claiming to be "built for AI" is actually Google with a wrapper. That's a problem, because AI agents don't search like humans. A human waits 1 second for a result. An agent making 50 sequential searches at 1 second each creates a 50-second lag. That kills the product. And latency is just one dimension: agents need semantic precision, structured outputs, and a range that spans sub-200ms real-time retrieval all the way to multi-step deep research. No human-facing search engine was ever designed to do that. Will Bryk, CEO of Exa, shares what he learned building a search engine from scratch for AI. He'll cover the architectural decisions behind Exa's latency spectrum, what real usage patterns look like across companies like Cursor, Notion, HubSpot, and Lovable, and why the benchmarks the field relies on today are dangerously inadequate for evaluating agentic search. The bigger argument: search is becoming the most critical primitive in AI infrastructure, and almost no one is building it right.
About the Search & Retrieval Track
Search & Retrieval sessions at AI Engineer World's Fair 2026 in San Francisco.
When
Tuesday, June 30, 2026
11:40 AM - 12:00 PM·20m
Where
Track 3 · Room 2003
Capacity: 250 attendees
Sign in to add this talk to your schedule.
Speaker
Will Bryk
Co-founder and CEO
Exa
@WilliamBryk
Will Bryk is building the next generation of search. As co-founder and CEO of Exa, he's chasing perfect search: an engine that gives every AI the highest quality information in the world, retrievable in milliseconds. Exa powers search for Cursor, Cognition, HubSpot, OpenRouter, and over 400,000 developers, and recently raised a $250M Series C at a $2.2B valuation from a16z, Benchmark, Lightspeed, Nvidia, and Y Combinator. Will grew up in New York City and studied CS and physics at Harvard, where he led the robotics club and dove into ML research. He founded Exa on one conviction: information is civilizational infrastructure, and if every AI can reach the best information, so can every human.