Project Details
GapFoundry
Portfolio Project
AI-powered competitive research platform that finds market gaps in minutes.
Overview
GapFoundry is an AI-powered competitive research platform that automates market gap analysis for founders, product teams, and agencies. You hand it a raw business idea or a competitor URL, and it condenses what is often a three-hour research workflow into minutes with a structured, cited report you can chat with and update.
Product Demo
The Problem
Manual competitive research means scraping reviews, mapping feature matrices, and hunting for market gaps across dozens of tabs. That routinely takes hours, so teams either skip it or do it shallowly. Generic LLM chat adds confident answers with no sources and no structure.
What It Does
- • Automated competitive research from a business idea or competitor URL
- • Structured reports with competitor profiles, feature analysis, and gap identification
- • Source citations on claims throughout the report
- • Confidence scoring that flags where the evidence is thin
- • Interactive chat over the generated research
- • Report updates when follow-up questions surface new angles
Design Focus
Autonomous research pipeline
Sequential web search, structured data extraction, and LLM analysis coordinated as a multi-stage agent rather than a one-shot prompt.
Interactive knowledge base
Users chat with the generated report, ask follow-up questions, and dynamically update the output as their understanding of the market evolves.
Data integrity
Confidence scoring and source citations on claims throughout the report, so users know what is well-supported and what needs manual verification.
What I Built
- • Multi-stage agentic workflow for search, extraction, and analysis
- • Hybrid web search orchestration across multiple providers
- • RAG pipeline over generated research reports
- • Structured output with citations and confidence scoring
- • Full-stack delivery with FastAPI backend and Next.js frontend
Tech Stack
Python | FastAPI | PostgreSQL | pgvector | LangGraph | LangChain | Docker | Next.js
Challenges
- • Turning messy web data into structured competitor analysis with named sources
- • Reliable research across broad market and specific competitor queries
- • Chat that updates reports, not just retrieves from them
- • Trust and verification in a domain where LLM hallucination is especially costly
- • Long-running agent jobs that stay resilient when individual steps fail