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.
Use WizardLM-2 with CAMEL to generate a complex, multi-agent drone attack simulation involving diverse drone types, coordinated movements, and evasive maneuvers. Use this simulation as input to your system. Evaluate the detection accuracy (mAP), tracking stability (MOTA), and the effectiveness of your threat prioritization module against this challenging scenario. Benchmark the end-to-end latency and FPS. Document your findings and propose further 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.
Build an AI-Driven Multi-Drone Threat Detection & Prioritization System
The proliferation of drones poses significant security challenges, necessitating advanced detection and neutralization systems. Inspired by the UK Royal Navy's adoption of drone-frying lasers, this challenge focuses on the critical 'sense and decide' component: an AI-driven system for real-time detection, tracking, classification, and prioritization of multiple drone threats from video feeds. Participants will develop a robust computer vision pipeline capable of identifying various drone types and assessing their threat level dynamically. This challenge involves building a Python-based application that processes simulated live video streams. The system must accurately detect and track multiple drones, classify them based on available visual features or metadata, and then prioritize them for potential engagement by a defensive system. Integration of a vector database like Qdrant will enhance drone identification and threat intelligence. A multi-agent simulation framework (CAMEL with WizardLM-2) will be used to generate diverse drone swarm scenarios for testing the system's resilience and decision-making capabilities.
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.