Your AI Agent Is Confidently Wrong About Production — Willem Pienaar, Cleric

Agents debugging production tend to report the first error log as root cause because there are no tests to push back. The talk gives specific grounding methods and outcome tracking to calibrate how far to trust them.

• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

• videoAgent Memory Is Solved. Agent Learning Isn't. — Karthik Ranganathan, Yugabyte
• videoEvals in AI: A Deep Dive — Tejas Kumar, IBM
• videoLifestyles of the AI-Native — Nick Nisi & Zack Proser, WorkOS
• videoAgentic Search vs Vector Search for Coding Agents: We Ran the Eval — Braintrust

• videoHow I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOSAI Engineer
• videoAgents, codebases, and teams — Aditya Khandelwal, Amazon AGI LabAI Engineer
• videoAlways-on agents run production without the on-call tax — Justin Smith, Resolve AIAI Engineer

Checking sign-in…

Loading comments…