Back to Prompt Library
testing
Structured Output & Evaluation Metrics
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AI Journalist for Government Meeting Analysis
Format
Text-first
Lines
1
Sections
1
Linked challenge
AI Journalist for Government Meeting Analysis
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Define the structured output format for the generated journalistic report (e.g., JSON schema including topics, speakers, decisions, and insights). Outline how you will quantitatively and qualitatively evaluate the accuracy of information extraction and the value of the journalistic insights, aligning with the provided evaluation module's metrics.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.
Tune next
Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.
Verify after
Make sure the prompt catches regressions instead of just mirroring the happy-path examples.