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.
Integrate Mistral Large 2 to act as a central strategic planner or a decision-making co-pilot for the factory. The LLM should receive summaries of the factory's state (resource levels, production backlog, agent status from DuckDB queries) and provide high-level directives or prioritize tasks for the agents, aiming to optimize overall throughput and resilience. Focus on crafting effective prompts to leverage Mistral Large 2's reasoning capabilities.
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 is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
Multi-Agent Resource Optimization for In-Space Factories
The advent of in-space manufacturing requires sophisticated autonomous systems for resource management, production scheduling, and failure recovery. This challenge focuses on developing an intelligent, multi-agent system to optimize the utilization of limited resources (power, raw materials, robot time) within an in-space manufacturing platform. The system must adapt to dynamic production demands, prioritize tasks, and handle unexpected events such as equipment failures or material shortages, aiming to maximize throughput and operational resilience. Participants will design and implement a simulation of an in-space factory featuring multiple manufacturing units and a shared resource pool. The core of the solution will involve leveraging Mistral Large 2 for high-level decision-making and strategic optimization, orchestrating agents within a multi-agent framework. `DuckDB` will be used for rapid, on-the-fly analytical processing of factory telemetry and resource logs to inform the AI's real-time decisions. The goal is to build a robust system that can efficiently manage production, minimize waste, and ensure the continuous operation of critical manufacturing processes in an autonomous and resilient manner, crucial for future domestic microelectronics production in space.
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.