Back to Prompt Library
testing
Evaluate Agent Performance and Routing with Libretto
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Real-time Personalized Sales Guidance
Format
Text-first
Lines
1
Sections
1
Linked challenge
Real-time Personalized Sales Guidance
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Create a test harness that simulates various sales scenarios, including complex objections and requests for detailed product information. Use Libretto's A/B testing and logging capabilities to evaluate how different prompt engineering strategies for Claude 4 Sonnet and Llama 4 Maverick impact the quality and relevance of sales guidance. Measure metrics such as response time, guidance accuracy, and the effectiveness of tool use. Provide examples of Libretto's observability logs showing model routing decisions and performance.
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.