Research and company-intelligence platform that ingests and deduplicates sources, extracts claims, and links every insight back to its supporting citations.
Competitor and market research is slow and scattered across many sources, with duplicated and conflicting information. AI-generated summaries make it faster but often cannot show where a claim came from, so teams cannot audit or trust the insights they act on.
Designed a research platform with a React and TypeScript front end and a FastAPI and PostgreSQL/pgvector back end. It ingests sources, normalises and deduplicates them, extracts claims, and links every insight to its supporting citations for auditability. Groq powers LLM processing; semantic embeddings and live search via Brave Search are optional and configurable. A Docker configuration is included for deployment. The platform supports competitor analysis and opportunity detection.
Every insight the platform produces is traceable to its source citations, so research outputs can be audited rather than taken on trust. Source deduplication and claim extraction turn scattered material into a structured knowledge base for competitor analysis and opportunity detection.
Every generated insight is linked to supporting citations, giving fully auditable research output.