Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 1 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
After the simulation, instruct the Blue Team's Incident Responder agent to compile a comprehensive report detailing any detected vulnerabilities, the Red Team's attack path, and concrete, actionable remediation steps. The report should also include an assessment of the Blue Team's detection accuracy and response time.
Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.
Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.
Make sure the prompt catches regressions instead of just mirroring the happy-path examples.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
Build a Competitive Multi-Agent System for Threat Analysis
This challenge tasks you with developing a sophisticated multi-agent system where specialized AI agents compete to identify and report security vulnerabilities. You will design and implement a team of 'Red Team' agents (attackers) and 'Blue Team' agents (defenders) using AutoGen, orchestrated to simulate a penetration testing scenario within a hypothetical enterprise network. The system will leverage Claude Opus 4.1's advanced reasoning capabilities for nuanced threat detection and mitigation strategies. The core of this challenge involves implementing robust agent-to-agent communication and MCP-enabled tool integration. Red Team agents will use tools to simulate reconnaissance and attack vectors, while Blue Team agents will utilize MCP-enabled tools to access simulated security logs, network configurations, and vulnerability databases to detect and counter threats. The objective is to evaluate the system's ability to autonomously identify vulnerabilities, propose effective remediations, and continuously adapt to evolving attack patterns.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.