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.
Using LlamaIndex, initialize a `SubQuestionQueryEngine` using `Mixtral 8x22B` as the primary LLM. Configure the engine to use a `VectorStoreIndex` for research papers and a `PropertyGraphIndex` for medical entity relationships. Define a custom tool called `medical_search` that the agent can use to perform multi-hop lookups.
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-Hop Medical Research Agent with LlamaIndex and Mixtral 8x22B
Inspired by the DEEPMED research on multi-hop medical search data, this challenge tasks you with building a medical research agent using LlamaIndex. You will implement a 'Turn-Controlled Agentic' reasoning loop where a Mixtral 8x22B model must decompose complex medical inquiries (e.g., drug-drug interactions involving secondary metabolic pathways) into discrete sub-queries. The agent will traverse a knowledge graph and vector store to synthesize evidence-based responses. Your implementation must prioritize factual accuracy and multi-step reasoning stability. You will leverage LlamaIndex's Query Pipelines and SubQuestionQueryEngine to handle the 'hop' logic, ensuring that each subsequent search is informed by the previous step's findings. The final output must include citations from a provided medical corpus and a confidence score for the synthesized conclusion.
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.