Experiment loop (autoresearch)

Hill-climb a measurable artifact: try → measure → keep-or-revert → log, on a branch, with a trail. Full procedure: references/sops/experiment-loop.md. Existing examples + use-case cards: experiments/.

First, the autonomy gate

Before looping unsupervised, confirm all three:

1. Objective, cheap, automatable metric (code computes it in seconds–minutes).
2. Reversible sandbox (git branch / throwaway data / .tmp).
3. No PHI, no confidential data, no external send, no prod deploy.

If any fails → human-in-the-loop: propose each change, get approval, no overnight run. Regulated/production outcomes feed the human-reviewed change process — never auto-deploy. This is CLAUDE.md's scale-caution-to-stakes rule.

Run it

1. Pick or write the experiment's CARD.md (objective, metric+direction, the one mutable surface, budget, autonomy, owner). New ones can copy experiments/forecast-tuning/.
2. git checkout -b experiments/<tag>.
3. Baseline run → tools/experiment_log.py add <results.tsv> --id ... --metric ... --status keep --note baseline.
4. Loop: edit the one mutable surface → run the read-only harness → log → keep (commit) if improved, else git reset. Simpler-and-equal = keep.
5. Stop on interrupt or the budget. Hand the winner + trail to the human.