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.
What you are building
The core problem, expected build, and operating context for this challenge.
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.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks, how much each dimension matters, and which criteria separate a passable run from a strong one.
JsonFormatCheck
Verify the output is a valid JSON matching the specified schema.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
SourcesCited
Ensure at least two distinct sources are cited in the output.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
AnswerAccuracy
Factual correctness and completeness of the answer compared to a ground truth (human-evaluated or via automated checks for simple facts). • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
SourceRelevance
Average relevance of cited sources to the generated answer. • target: 4.5 • range: 1-5
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Master LlamaIndex for building sophisticated RAG pipelines, including data ingestion, indexing strategies (vector, keyword, hierarchical), and query engines
Implement a LlamaIndex agent capable of dynamically selecting and using various tools (e.g., web scraping, document parsers, database connectors) for M&A-specific data retrieval
Design and configure query engines within LlamaIndex to leverage Gemini 2.5 Pro for advanced reasoning, summarization, and synthesis of retrieved information
Utilize Skyvern as a LlamaIndex tool to automate the extraction of financial data, news articles, and competitive analysis reports from public websites for due diligence
Integrate Ollama for local embedding generation and/or local LLM inference during development and testing, allowing for faster iteration and reduced API costs
Develop strategies for handling semi-structured and unstructured data, using LlamaIndex's capabilities to extract key entities and relationships relevant to M&A analysis
Build a multi-modal RAG capability within LlamaIndex to potentially process visual information (e.g., charts, infographics) alongside text-based documents for comprehensive analysis
Implement evaluation metrics and logging within LlamaIndex to monitor retrieval accuracy and agent performance during complex due diligence queries
[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsAI Research & Mentorship
Participation status
You haven't started this challenge yet
Operating window
Key dates and the organization behind this challenge.
Find another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.