Back to Prompt Library
planning
AutoGen Multi-Agent System Setup
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AI Cyberattack Breakthrough Evaluator
Format
Text-first
Lines
1
Sections
1
Linked challenge
AI Cyberattack Breakthrough Evaluator
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Set up an AutoGen multi-agent conversation with at least two agents: a 'Red Team Attacker' and a 'Blue Team Defender'. Define their roles, capabilities, and initial goals. The 'Red Team Attacker' should aim to find vulnerabilities, while the 'Blue Team Defender' should aim to identify and mitigate them. Outline their communication protocol and how they'll collaborate on a given security challenge.
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 role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.