11. Stop Telling Agents How — Dan Barrett, Raymond Weitekamp & Jose Montes de Oca, OpenProse Say what you want, not how to get it. The OpenProse team shows how to write multi-agent workflows as declarative contracts in plain markdown, which any harness (Claude Code, Codex 10/19 03:00 ♡
12. Insurance Claims Are AI's Messiest Data Problem — Denys Linkov, Wisedocs Insurance claims are full of handwriting, faxes, duplicates and 8GB PDFs. Denys Linkov of Wisedocs explains why that unstructured data is both the biggest barrier and the biggest o 10/18 17:00 ♡
13. Evals for High-Stakes AI Agents — Doneyli De Jesus & Annabell Schäfer, Langfuse A hands-on workshop on evaluating AI applications where mistakes are expensive. Annabell Schäfer and Doneyli De Jesus from Langfuse use a banking assistant to walk through the whol 10/18 16:00 ♡
14. Teach Your Agent to Prove It's Done — Nick Nisi & Zack Proser, WorkOS Your agent says it's done. Is it? Nick Nisi and Zack Proser from WorkOS show how to build verification loops that let coding agents check their own work. They cover clear goals, CL 10/18 15:00 ♡
15. An AI Agent Got Its User Banned From Resy — Keycard, JPMorgan Chase & AAuth An AI agent trying to book a restaurant made 200 calls in 90 minutes and got its own user banned from Resy. It had good intentions. It just had no limits. Keycard's Allie Howe mode 10/18 07:00 ♡
