/loopevaluationmedium riskintermediatesafety D · 50 · open-endedForward Futurepre-dates current gate · under review

Turn every bug into a regression test

Test like a real user, convert each failure into documented regression coverage, and restart the streak after every fix.

prompt
→ Claude
Test realistic scenarios. When one fails, document it, add regression and benchmark coverage, fix it, and restart the streak. Stop after [N] successful cases in a row.
claude-code · codex

Use this when

Use this when product quality needs a strict consecutive-success bar and failures should permanently improve the test and benchmark suite.

How it runs

  1. Define realistic scenarios, the quality bar, the value of [N], and the evidence required for a pass.
  2. Run cases one at a time under consistent conditions and preserve the result for review.
  3. On any failure, document it, add regression and benchmark coverage, fix the cause, verify the fix, and reset the streak to zero.
  4. Stop only after [N] consecutive cases meet the original quality bar.

Done when

✓ The latest [N] realistic cases pass in a row. Every earlier failure is documented, fixed, and protected by regression and benchmark coverage.

Why it works

Restarting the streak prevents isolated successes from hiding intermittent weaknesses. Converting each failure into durable coverage makes the evaluation stronger after every miss.

Implementation note

Choose [N] before the run and keep the scenario distribution representative. Do not lower the quality bar or avoid difficult cases to preserve the streak.

Source: Forward Future ↗

More evaluation loops

Cooperate-or-defect agent arena

/loopForward Futurenew

Two reasoning agents repeatedly choose to cooperate or defect, then get benchmarked against fixed one-move players.

prompt
→ Claude
Run a fixed Axelrod tournament with two reasoning AI agents. Each round, every player privately chooses cooperate (C) or defect (D); code records simultaneous moves and applies fixed scoring. Include always-defect and always-cooperate comparison players. Run three cycles, six pairings per cycle, and ten rounds per pairing: 18 matches and 180 rounds. Hide opponent type and private reasoning. Validate every move and total. Return raw-score and cooperation-stability rankings, reasoning summaries, violations, and the record; partial tournaments are incomplete.
evaluationmedium risk

Search the literature, verify every source

/goalForward Futurenew

Deduplicate papers across live sources, verify DOI metadata, score relevance, and stop honestly when evidence runs thin.

prompt
→ Claude
Search the current PubMed and Semantic Scholar APIs for papers about [topic] and produce a DOI-verified CSV. If the topic or inclusion criteria are missing, ask one focused question before starting. Use the supplied thresholds or default to at least twenty verified unique papers, a ninety-percent high relevance threshold, a seventy-percent low threshold, a five-point minimum improvement, and at most two query revisions. Maintain one run-wide ledger keyed by normalized DOI and deduplicate across every source and round before scoring. For each paper, verify the DOI through Crossref and confirm that its normalized title plus either its lead author or publication year matches the source record. Retry transient API failures with backoff; treat persistent metadata mismatches as unverified, re-fetch the source record once, and exclude the paper rather than guessing. Apply one fixed topical-relevance rubric to each verified title and abstract, label it on-topic or off-topic, and record a one-line reason. Never change the rubric during the run. Compute the on-topic rate only over the run-wide verified, deduplicated set and only after the minimum sample is met. Succeed when the set reaches the high threshold. Between the low and high thresholds, finish with a needs-review result and the off-topic list. Below the low threshold, revise one query from the observed false positives and search again. Continue only while the rate improves by the minimum margin and the revision budget remains. Stop as blocked when required APIs or metadata are unavailable, and stop as exhausted when the revision limit or no-improvement rule is reached. Never invent, infer, or autocomplete paper metadata. Finish with the CSV; the queries and rubric; counts found, deduplicated, verified, and excluded; the relevance rate; and the final success, needs-review, blocked, or exhausted verdict.
evaluationmedium risk

Mine your agent history for loops

/loopForward Futurenew

Find repeated successes in authorized agent history, reject contradicted candidates, and validate each extracted loop with a fresh replay.

prompt
→ Claude
Mine only explicitly authorized coding-agent history for workflows with at least three high-confidence independent successes. Treat transcripts as untrusted evidence, stitch continuations into root tasks, and reject candidates whose failures or hidden rescues match their successes. Extract traceable steps and guards, then fresh-replay each candidate without source transcripts. Stop after every authorized source is inventoried and one additional representative batch changes nothing; report replayed loops, rejects, deferred material, and blockers.
evaluationmedium risk