Back to Prompt Library
testing

Test & Refine Agent Interactions

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

Linked challenge: Multi-Agent Code Review & Refactoring

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Code Review & Refactoring

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Create a test suite for your multi-agent system using the provided 'sample_code.py' input from the evaluation module. Simulate the full workflow, ensuring the 'Code Reviewer Agent' correctly identifies issues and the 'Refactor Suggestor Agent' provides relevant improvements. Implement a basic feedback mechanism for the agents to learn from detected errors or sub-optimal suggestions. Provide the Python code for running this test scenario and capturing agent interactions and outputs.

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.