Review
Review Findings for Evidence Strength
Review the findings section of a report for evidence quality.
||
You are a senior MEAL specialist reviewing the findings section of a draft report for your program with a narrow focus on evidence strength.
**FINDINGS SECTION TO REVIEW:**
[paste findings section here]
**Review Requirements:**
1. **Claim and evidence pairing.** For each major finding, check that the claim is matched to a specific evidence base (quantitative data, qualitative quotes, document review, observation). Flag claims without traceable evidence.
2. **Triangulation.** Assess whether findings rest on more than one source or method, especially where claims are strong.
3. **Disconfirming evidence.** Check whether the section acknowledges evidence that contradicts the headline claim, or whether it cherry-picks supportive data.
4. **Inference discipline.** Distinguish among descriptive, analytical, and judgmental statements. Flag where inference outruns the evidence.
5. **Data quality flags.** Identify findings that rest on weak data (low response rate, single source, recall bias) without acknowledging the limitation.
6. **Disaggregation use.** Check whether disaggregated patterns are surfaced or averaged away.
**Output Format:**
Produce:
1. A 1-paragraph overall assessment of evidence strength.
2. A finding-by-finding review table: finding, evidence basis, strength rating (strong/moderate/weak), recommended action.
3. A prioritized revision list (must-fix vs. should-fix).
4. A short note on findings that should be downgraded or removed if stronger evidence cannot be produced.
Review the outputFindings Evidence Strength
reviewevaluationanalysisquality-assurance
Scoring Rubric
Findings Evidence StrengthUse this rubric to score and improve the AI output from this prompt.
Related Guides
- How to Code Qualitative Data with AI
Turn 30 pages of interview transcripts into validated themes in 2 hours instead of 3 weeks. A 4-step workflow that pairs AI pattern recognition with human analytical judgment.
- How to Use AI for Baseline and Endline Analysis
Comparing baseline and endline data is the backbone of impact measurement. AI can run the comparisons, flag anomalies, and draft the narrative, but only if you structure the analysis around specific evaluation questions.