Back to Prompt Library
testing
System-Wide Test and Refinement
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: MCP-Enabled Drug Design Agent
Format
Text-first
Lines
1
Sections
1
Linked challenge
MCP-Enabled Drug Design Agent
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Run the complete multi-agent system with the provided 'Autonomous Scientific Design' sample input. Analyze the reasoning path and final output. Identify bottlenecks or areas where agents might get stuck and propose modifications to the LangGraph state or agent logic to improve robustness and design quality.
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.