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.
Translate your hierarchical plan into a LangGraph workflow. Define the nodes for each phase (e.g., 'generate_hypothesis_node', 'search_candidates_node', 'predict_properties_node'), the edges connecting them, and the state schema that will be passed between nodes. Ensure the workflow can handle conditional transitions based on evaluation results.
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.
Hierarchical Planning Agent for Molecular Discovery with DeepSeek-V3, LangGraph, and Redis Vector
This challenge addresses the complex problem of closed-loop molecular discovery by tasking developers to build an intelligent agent capable of hierarchical planning. Inspired by "SCOPE: Language Models as One-Time Teacher for Hierarchical Planning" and "Toward Closed-loop Molecular Discovery," the agent will decompose high-level scientific goals (e.g., "design a molecule with specific properties") into actionable sub-tasks. The system will leverage DeepSeek-V3 as its core reasoning engine, orchestrated by LangGraph for dynamic workflow management and state tracking. A Redis Vector database will serve as a dynamic knowledge graph, integrating molecular data, chemical reactions, and property predictions, enabling RAG-enhanced reasoning and strategic search. ZenML will be used to track experimental outcomes and model iterations, simulating a closed-loop discovery process.
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.