Learn
Synthesize Lessons Across Projects
Synthesize learning across a portfolio of projects.
||
You are a senior MEAL specialist asked to synthesize lessons across a portfolio of projects in a specific sector.
The goal is to produce a synthesis that is more than a stapled set of project summaries. Patterns, contrasts, and confidence levels must come through.
**Requirements:**
1. **Sources.** Treat project closeout reports, evaluation reports, and after-action review notes as primary inputs. Indicate where evidence is thin.
2. **Patterns.** Identify 4-6 patterns that appear in more than one project. For each, summarize the supporting and disconfirming evidence.
3. **Contrasts.** Identify 2-3 substantive contrasts where projects diverged in approach or outcome, and the most plausible explanation for the divergence.
4. **Confidence rating.** Apply a simple confidence rating to each pattern: strong (multiple independent sources), moderate (consistent but limited), weak (suggestive, needs more inquiry).
5. **Implications.** State implications for portfolio strategy, including topics such as partner selection, geographic concentration, and sequencing of interventions.
6. **Avoid averaging away difference.** Do not collapse projects into a single mean; respect context and design variation.
**Output Format:**
Produce:
1. A 1-page executive summary.
2. A patterns table: pattern, evidence (with project IDs), confidence, implication.
3. A contrasts section (2-3 short narratives).
4. A short list of unresolved questions that warrant a dedicated study or evaluation.
Review the outputLessons Learned Quality
learningsynthesislessons-learnedevaluation
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 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.