Back to Prompt Library
testing
Test & Refine Policy Violation Detection
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build MCP-Enabled Social Media Policy Enforcement Agents
Format
Text-first
Lines
1
Sections
1
Linked challenge
Build MCP-Enabled Social Media Policy Enforcement Agents
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using the provided `sample_input` for the `PolicyViolationDetection` task, run your system. Analyze the `alerts` generated. Refine your agent logic, RAG implementation, and MCP tool calls to improve precision and recall in detecting policy violations. Pay close attention to the reasoning provided by the agents and their adaptive budget usage.
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.