About
Justin Chavez is Head of Applied AI Engineering at Inkeep (YC W23), where he builds the agent platform used in production by Anthropic, Midjourney, Clay, Pinecone, PostHog, and others. He also operates agent-powered systems for Inkeep's own GTM — 18 months on both sides of the agent infrastructure problem. Previously a founding engineer at two startups, both acquired (Reverie Labs by Ginkgo Bioworks, Miner & Kasch by Atos), and Operations Tech Lead at U.S. Digital Response. He organizes Code and Coffee SF, a 2,600+ member builder community.
Sessions
Agents Don't Collaborate Like Humans. Stop Building Like They Do.
What you will learn:
-Agents aren't users of your software — they're operators. Build infrastructure accordingly. -Every time you move context from a product surface to an open interface, your agent system gets more capable. This compounds. -The line between good and bad agent infrastructure isn't local vs cloud — it's whether an agent can operate on the interface directly without product-imposed constraints. -The MCP ecosystem is solving connector logistics. The harder problem is environment design — giving agents space to think, not just endpoints to call. -A practical litmus test for your stack: if an agent can't query it, extend it, or rewrite it, it's working against you.