Log everything in agent apps: scheduled reviews to fix prompt confusion

jasonkneen · x · 2026-08-18

Jason Kneen shares a practical workflow for agent-based apps: logging is vital for accountability, evals, and "self-healing". He records all activity during development, then runs a scheduled task that lets the app or build agent review these logs regularly, spot communication confusion between user and agent, and adapt the system prompts and code accordingly.

Related event: Logging is the cornerstone of accountability, evals and self-healing in agent apps(2 posts)→

Original post →

More from coding & agent

coding & agent channel →