Recommendation Traceability Audit
Check that each recommendation links to evidence and each finding has an action.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Check traceability in a research report. Findings with evidence: [FINDINGS]. Recommendations: [RECOMMENDATIONS]. Decisions the team must make soon: [DECISIONS]. For each recommendation find the finding that supports it and note the strength of that evidence, such as how many participants showed the problem or how many data points support the pattern. Flag recommendations with no finding behind them, findings that nobody acts on, and recommendations that go further than the evidence allows. Estimate effort and the cost of being wrong if the finding is weaker than it looks. Return a traceability table with Recommendation, Supporting finding, Evidence strength, Effort and Risk, a list of orphans in both directions, and a revised priority order. Do not add findings of your own. Add a worked row with invented content: Recommendation, shorten the signup form to five fields; supporting finding, 7 of 10 participants hesitated at the phone number field and 3 gave up; evidence strength, strong; effort, low; risk if the finding is wrong, low. Another: Recommendation, redesign the whole navigation; supporting finding, one participant said the menu was confusing; evidence strength, weak; effort, high; risk, high, so run a card sort first. Count: of 12 recommendations, 3 have weak or no evidence, 25 percent. Add a closing step: link every recommendation in the final report to its finding number so readers can follow the evidence.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.