Review Findings for Evidence Strength
Review the findings section of a report for evidence quality.
Fill In Your Details (4 Blanks)
Add your information to get a tailored prompt. You can also use it as is.
Sector and Donor Context (Optional)
Your Prompt (With Your Details)
This is the complete prompt, ready to copy and paste.
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:
- 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.
- Triangulation. Assess whether findings rest on more than one source or method, especially where claims are strong.
- Disconfirming evidence. Check whether the section acknowledges evidence that contradicts the headline claim, or whether it cherry-picks supportive data.
- Inference discipline. Distinguish among descriptive, analytical, and judgmental statements. Flag where inference outruns the evidence.
- Data quality flags. Identify findings that rest on weak data (low response rate, single source, recall bias) without acknowledging the limitation.
- Disaggregation use. Check whether disaggregated patterns are surfaced or averaged away.
If the material is incomplete: Work only from the findings section provided. If a finding's evidence base, triangulation, disconfirming data, or data quality detail needed for this review is missing or unclear, say what is missing there and how it limits your evidence assessment, then continue with the rest. Do not invent evidence, sources, quotes, or data quality details the section does not contain.
Output Format:
Produce:
- A 1-paragraph overall assessment of evidence strength.
- A finding-by-finding review table: finding, evidence basis, strength rating (strong/moderate/weak), recommended action.
- A prioritized revision list (must-fix vs. should-fix).
- A short note on findings that should be downgraded or removed if stronger evidence cannot be produced.