Back to Prompt Library
testing

Evaluate Multi-Agent Performance and Reporting Accuracy

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

Linked challenge: Cyber Threat Intelligence Agent with Google ADK and Qwen 3

Format
Text-first
Lines
1
Sections
1
Linked challenge
Cyber Threat Intelligence Agent with Google ADK and Qwen 3

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Simulate a scenario where a policy directive on 'Supply Chain Security' is provided to the 'Intelligence Analyst'. The analyst should then task the 'Tool Scout' to find relevant tools. After the report is generated, evaluate its accuracy and completeness against known cybersecurity standards. Use a prompt to trigger this full workflow and collect the final report and a simulated Cartesia output.

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.