Review
Review Data Visualization Quality
Review the charts and figures in a report for chart-type appropriateness, labeling completeness, honest scaling, accessibility, and caption quality.
||
You are a senior MEAL specialist with data visualization expertise, reviewing the charts and figures in a report. If the document contains text descriptions of charts rather than the charts themselves, review based on the descriptions.
**REPORT WITH VISUALIZATIONS TO REVIEW:**
[paste report or figure descriptions here]
**Review Requirements:**
1. **Chart type appropriateness.** Check whether each chart type matches the data relationship it is showing (comparison, distribution, composition, trend, relationship), not chosen out of habit or for visual variety.
2. **Labeling completeness.** Verify titles, axis labels with units, legends, data sources, and time periods are present so each visualization is interpretable on its own.
3. **Honest scaling.** Assess whether axes, scales, baselines, and intervals are chosen honestly rather than truncated, stretched, or distorted to exaggerate or downplay differences.
4. **Accessibility.** Check that color choices are colorblind-safe, contrast is sufficient, and color is paired with shape, pattern, or label so meaning is not lost.
5. **Caption quality.** Verify each visualization has a caption that interprets the data and tells the reader what to take away, not only describing what the chart contains.
6. **Integrity and clarity.** Flag any visualization that misrepresents the data, hides underperformance, or would confuse a non-technical reader.
**Output Format:**
Produce:
1. A 1-paragraph overall assessment.
2. A scored review table: dimension, score (1-5), evidence from the report (figure number or description), recommended action.
3. A prioritized revision list (must-fix vs. should-fix), keyed to specific figures.
4. A short note on whether the visualizations are ready for publication or require another revision round first.
Review the outputData Visualization Quality
reviewdata-visualizationchartsreportingevaluation-report
Scoring Rubric
Data Visualization QualityUse this rubric to score and improve the AI output from this prompt.
Related Guides
- How to Use AI for Donor Reporting
Donor reports consume more M&E staff time than any other deliverable. AI can extract findings from data, draft narrative sections, and format compliance tables, but only if you feed it the donor template structure and your actual results.
- How to Draft Evaluation Reports with AI
Stop staring at a blank page. A 4-phase workflow turns your completed analysis into donor-ready evaluation narrative in hours, not days.