Document a Program Failure
Document and structure learning from a program that did not meet its targets.
Draft it, check it, fix it
Three prompts for one job: draft with this prompt, score the result against its rubric, then revise what scored low.
||
You are a senior MEAL specialist documenting learning from a program that did not meet its targets.
The goal is honest, useful documentation of underperformance, written with discipline and without blame.
**Requirements:**
1. **State the underperformance.** Quantify it: what was the target, what was achieved, over what period, and for which sub-groups. Avoid softening language.
2. **Root-cause analysis.** Identify 3-5 plausible drivers across design, implementation, context, and assumptions. For each, provide supporting evidence and counter-evidence.
3. **What was tried.** Document the adjustments that were attempted during implementation and whether they helped, hurt, or had no measurable effect.
4. **Counterfactual reflection.** Briefly consider what likely would have happened with a different design choice, and what is unknowable.
5. **Lessons.** Translate the analysis into 4-6 lessons. Each must be specific and decision-oriented. Avoid generic statements such as 'we needed more time.'
6. **Tone.** Factual, accountable, blame-free. Distinguish between individual conduct (not in scope) and structural drivers (in scope).
**Output Format:**
Produce:
1. A short framing paragraph.
2. A performance table (target, actual, gap, period, sub-group note).
3. A root-cause section with evidence per driver.
4. A 'what was tried and what happened' table.
5. A lessons list, with each lesson tagged to the decision it should inform.
Review the output withLessons Learned Quality
Scoring Rubric
Lessons Learned QualityUse this rubric to score and improve the AI output from this prompt.
Related Prompts
Learn More
Related Guides
- How to Code Qualitative Interview Data with ChatGPT
Turn 30 pages of evaluation interview transcripts into validated themes in 2 hours instead of 3 weeks. A 4-step workflow that pairs AI pattern recognition with the human analytical judgment that makes the findings defensible.
- 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.