Back to Prompt Library
testing

Evaluation and Refinement

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Agent for Personalized Market Insights with Voice UI

Format
Text-first
Lines
1
Sections
1
Linked challenge
Agent for Personalized Market Insights with Voice UI

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Run your complete agent system with the sample input for the 'Personalized Investment Query' task. Capture the voice response transcript and the JSON summary. Critically evaluate the agent's performance in terms of accuracy, personalization, and conversational flow. Suggest potential improvements, especially regarding how the agent handles ambiguous queries or multiple tracked entities. Provide the final runnable Python code.

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.