Modulai built an agentic research system for a leading European investment firm that enriches reports by performing iterative research. It autonomously analyzes documents, reasons about potential gaps, and conducts structured investigations to surface overlooked insights and recent developments, providing a more complete picture for high-stakes decision-making.
Challenge
Critical business decisions rely on detailed reports such as investment analyses or legal briefs. However, these documents often contain hidden gaps, outdated information, or unstated assumptions. Acting on this incomplete picture creates significant risk and can lead to missed opportunities. Manually enriching these documents is too slow and expensive to be practical.
Solution
The system takes a finished report and works out what is missing from it, generating its own research questions, investigating them across the public web and internal knowledge bases, and folding what it finds back into a single consolidated document. This merges the original content with newly discovered insights grounded with references, giving users a more complete and reliable basis for action.
Tools
The system uses large language models within a custom multi-agent architecture employing the ReAct (Reason + Act) framework. Agents reason and use tools including web search APIs, an internal RAG service, and a generation tool for follow-up questions. Built entirely in Python, the system ensures transparency, traceability, and flexible citation management throughout the research process.
Value created
For an investment firm, this solution means decisions rest on a more complete and current picture, catching the gaps, outdated figures, and unstated assumptions that manual review is too slow and costly to chase down reliably.
Learn more
