Turn past agent transcripts into durable coding rules and skills

zeeg · x · 2026-07-26

A practical workflow for improving coding agents: feed them a chunk of past transcripts, ask them to find recurring failure patterns, then have them suggest durable fixes such as new prompt guidance, skills, or AST-grep rules. The author says this worked on Warden’s code-quality loop, though the output may still include hallucinations and requires manual judgment.

The core idea is to turn your own interaction logs into a feedback loop:

The takeaway is that LLMs are strong at pattern matching and repetitive work, so transcript mining can make them much more effective over time.

Original post →

More from coding & agent

coding & agent channel →