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.
Detail the A2A communication protocol your agents will use for coordination and task hand-offs. Specify how agents will utilize MCP-enabled tools to interact with simulated ERP, IoT sensor data feeds, and a SCADA system. Provide example function signatures for key MCP tools (e.g., `get_sensor_data(sensor_id)`, `update_production_schedule(product_id, quantity)`).
Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Hold the task contract and output shape stable so generated implementations remain comparable.
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.
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 already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
Autonomous 'Dark Factory' Orchestration with Claude Opus 4.5 and CrewAI
As global manufacturing shifts towards fully autonomous 'dark factories,' the need for advanced AI orchestration becomes paramount. This challenge involves designing and implementing a multi-agent system that can autonomously manage and optimize operations within such a factory. Participants will create a CrewAI-based team of specialized agents responsible for predictive maintenance, supply chain resilience, production scheduling, and quality control. The system will rely on Claude Opus 5 for its superior long-context reasoning to analyze vast streams of IoT sensor data, historical performance logs, and complex supply contracts. Agents will communicate using an A2A (Agent-to-Agent) protocol, making decisions and executing actions across various simulated industrial systems. A central component will be the integration of the MCP to enable seamless, real-time interaction with enterprise resource planning (ERP) systems, SCADA (Supervisory Control and Data Acquisition), and IoT platforms, allowing agents to retrieve and update critical operational data. This solution will demonstrate the power of generative AI in orchestrating complex industrial processes, minimizing downtime, and adapting to unforeseen challenges in a truly autonomous 'dark factory' environment.
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.