An AI Agent Got Its User Banned From Resy — Keycard, JPMorgan Chase & AAuth

Frames agent access control as missions and budgets rather than coarse OAuth scopes, with a concrete failure case, relevant to anyone giving agents real credentials.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• videoEvals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse
• videoTeach Your Agent to Prove It's Done — Nick Nisi & Zack Proser, WorkOS
• videoHow to Know If Your AI Agent Is Any Good: Evals With Phoenix & Claude — Laurie Voss, Arize AI
• videoInsurance Claims Are AI's Messiest Data Problem — Denys Linkov, Wisedocs

• videoWhy One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, AnthropicAI Engineer
• videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOSAI Engineer
• videoAI Agents Don't Read Your Policy Docs. They Hit Your APIs — GraviteeAI Engineer

Checking sign-in…

Loading comments…