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 9 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.
Modify your LlamaIndex setup to explicitly use Ollama for generating embeddings (`OllamaEmbedding`). Describe the benefits of this approach (e.g., local control, cost savings). Ensure your `VectorStoreIndex` is built using these embeddings and demonstrate that your agent still performs accurately. Provide the updated configuration snippet. ```python from llama_index.core import Settings from llama_index.embeddings.ollama import OllamaEmbedding # Configure OllamaEmbedding Settings.embed_model = OllamaEmbedding(model_name="nomic-embed-text", base_url="http://localhost:11434") # Re-initialize index or ensure existing index uses this setting # ... (rebuild index if necessary or ensure it loads with new setting) ```
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.
Agent for Enterprise M&A Due Diligence
This challenge focuses on building an advanced RAG-powered agent using LlamaIndex for enterprise M&A due diligence, inspired by the news of cloud providers acquiring AI search companies to enhance agent capabilities. Participants will create an intelligent agent capable of querying internal and external knowledge bases to gather, synthesize, and analyze critical information pertinent to a potential acquisition target. The agent will need to handle diverse data types (documents, web pages, internal reports) and provide concise, actionable insights. The system should demonstrate sophisticated retrieval augmentation, dynamic tool selection, and the ability to answer complex, multi-hop questions about a target company's financials, market position, and technological landscape. This requires leveraging LlamaIndex's advanced indexing, query engine capabilities, and agent orchestration to ensure accurate and up-to-date information retrieval.
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.