Act like a first-time user of [product]. Start at the real entry point in a clean session with no saved login, site data, remembered route, or hidden setup. Complete onboarding using only visible guidance and record obstacles. Fix the worst one with the smallest change that preserves every security, access, and product requirement. Discard the session and retry. Stop after one uninterrupted success, no safe fix, blocked access, or required approval. Return the path, changes, evidence, and blockers.
claude-code · codex
Use this when
Use this when new users may face unclear instructions, hidden assumptions, difficult recovery, or unnecessary steps that experienced users no longer notice because their accounts and browsers remember earlier setup.
How it runs
Open a clean session with no saved login, cookies, site storage, remembered web address, secret setup, or repair left over from an earlier attempt.
Begin where a real newcomer begins, complete the onboarding steps using only visible guidance, and record anything unclear, unexplained, unnecessarily difficult, or impossible to recover from.
Fix the most harmful obstacle with the smallest change that preserves security, access, legal, onboarding, and product requirements.
Throw away the session and retry the entire experience until one uninterrupted clean pass succeeds or no safe progress is possible, access is blocked, or approval is required.
Done when
✓ A first-time user can complete onboarding in one uninterrupted clean session. The full experience succeeds from the real starting point without saved browser state, secret setup, guessed routes, or manual repairs, and every real requirement remains intact.
Why it works
Saved logins and remembered setup hide problems from experienced users. Starting over after every fix shows whether the product itself now explains the path, while preserving real requirements prevents an easier experience from weakening security or access controls.
Implementation note
A clean session means a new private browser or another isolated environment with no cookies, login, local storage, cache, or remembered route. Start where a newcomer would actually arrive and follow only the guidance the product exposes.
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.
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.
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.