The self-improving champion loop
A prompt-optimization workflow that tests challengers on a working set, promotes only fresh holdout wins, and keeps the current champion on uncertainty.
High Quality
New
Join 0+ developers using this skill
This loop is republished with attribution. Full credit and the original content belong to the source linked above.
command
Loops & Automation
intermediate
AI Skill Market Insights
Real data. Real impact.
Popularity
Rising
Emerging
Active Users
0+
Developers
Kickoff Prompt
Copy this prompt and run it with your agent to start the loop.
Improve a prompt, policy, or configuration. A support assistant's system prompt is one example. Save the champion, its score, a working set, untouched holdout cases, must-pass checks, and [budget]. Each round, change one thing based on a recorded failure. Promote the challenger only if it beats the champion on holdouts by [margin] without weakening a must-pass check; otherwise keep the champion. Stop at the target, budget limit, or no progress. Return the winner, scores, experiment log, and remaining failures.TEAR & SHARE
2-3hrs/WK
RISING
0.0K+ USING
Tags
agent:claude-code
tag:evaluation
jose-c-munoz
self-improving-loop
champion-challenger-evaluation
goodhart-prevention
independent-evaluation-gate
bounded-optimization-workflow
forward-future
loop
