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 2 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, design and implement a data ingestion pipeline that can pull data from a simulated legal document repository (e.g., local PDF files for filings), a news API (simulated with local JSON files), and a public company website (simulated via web scraping of a local HTML file). Your task is to use `SimpleDirectoryReader`, `WebPageReader`, or custom `BaseReader` implementations to load these documents, and then create a `VectorStoreIndex` using `PineconeVectorStore` for efficient retrieval. Provide Python code snippets for initializing LlamaIndex, defining your readers, and setting up the index.
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.
LLM-Powered Legal & Market Intelligence
Develop an advanced RAG-powered agent system using LlamaIndex to analyze complex legal filings and market intelligence related to high-profile disputes, such as the Elon Musk vs. OpenAI/Microsoft lawsuit. The system will ingest diverse data sources - legal documents, news articles, company statements, and financial reports - to provide comprehensive summaries, strategic insights, and historical context. This challenge emphasizes LlamaIndex's capabilities in multi-document retrieval, hierarchical indexing, and agentic query planning to navigate vast, unstructured datasets. The solution requires designing a robust data pipeline that connects various enterprise data sources, indexes them effectively for semantic search, and employs an agentic query engine to synthesize information. Participants will build custom tools for data extraction and transformation, ensuring the LLM (GPT-4o) can access and reason over highly specific and sometimes contradictory information to generate accurate and actionable intelligence reports.
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.