In this pattern an agent’s behaviour improves by editing a text file, not the model. A second, scheduled agent reads human feedback on the first agent’s work and opens a pull request that changes the skill file the first agent reads. There is no fine-tuning, embeddings store, or memory service.1

The problem it solves

Warp’s code review agent, used across roughly 800,000 monthly developers, kept making suggestions engineers had already rejected: the reviewer’s explanation lived in one session’s context and was discarded, so the next run read the same instructions.1

Two loops

Inner loopOuter loop
RunsPer task (every PR)On a schedule, over many past runs
ReadsThe skill file, the diff, repository contextAccumulated feedback and the skill file
ProducesThe code reviewA small, focused edit to the skill file
Applied byImmediately, in the sessionA pull request a person merges

As described in the source.1 The outer skill never does the task; it compares what the agent suggested with how people responded and proposes an edit.1

Feedback quality over volume

A thumbs-down says the output was wrong but not why. A comment such as “our convention is that this kind of global variable uses this naming pattern” states a rule the improver can write into the skill. A small amount of detailed feedback from a senior engineer is worth more than a large volume of cursory ratings.1

Adopting it

  1. Keep the agent’s instructions in a file in the repository.
  2. Capture feedback as text, attached to the run it answers.
  3. Write the improver as its own skill: read feedback since the last run, compare with the skill file, propose one small edit, open a PR.
  4. Schedule it; per-task improvement has too little evidence and churns.
  5. Review the PRs, rejecting one reviewer’s preference presented as team convention.

1

Where it breaks down (analysis from the source)

The note’s author lists: skill files that grow into long, partly contradictory lists without periodic pruning; overfitting to the people who write the most feedback; product complaints turned into skill rules; and no measurement after merge, so a bad change shows up only slowly in later feedback.1

Footnotes

  1. How Warp Builds Self-Improving Agents on Claude 2 3 4 5 6 7