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.
As the 'Security Engineer' agent, after the incident response is complete, review the 'IncidentResponsePlanning' output from the 'Security Orchestrator'. Identify any weaknesses in the plan, areas where the RAG system could be improved, or processes that could be automated. Propose enhancements to the agent system's capabilities or the underlying knowledge base for future incidents. Submit a brief report outlining these improvements.
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.
Orchestrate a Factual Multi-Agent System for Cyber Threat Response
This challenge involves developing a multi-agent system that simulates a cybersecurity incident response team. Inspired by the need for factual accuracy in AI (as highlighted by benchmarks like FACTS) and the potential for AI in cybersecurity, participants will build a system where agents collaboratively detect, analyze, and propose mitigation strategies for simulated cyber threats. A critical requirement is the integration of a robust RAG (Retrieval Augmented Generation) mechanism using a Pinecone vector database. This RAG system will ground agent reasoning in up-to-date, factual cybersecurity intelligence, effectively combating LLM hallucinations that could lead to erroneous or dangerous security advice. The system will leverage a capable LLM like Llama 3.2 (via Replicate) and an orchestration framework like CrewAI or AutoGen. Success will be measured by the system's ability to accurately identify threats, minimize generated misinformation, and produce actionable, contextually relevant, and factually sound incident reports and mitigation plans.
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.