GhostReport
Team chanitnan kitnantakhun
The big news
Product teams finally learn why users leave, not just where. GhostReport is an evidence layer for existing apps: AI reads the source code to map workflows and find steps nobody tracks, checks the logs first, and asks users one short, skippable question only where logs can't answer. It drafts competing hypotheses, locks them, then tests them. The result is an auditable report where every number traces back to recorded events or a line of code. It's ideal for fintech and Web3 onboarding gates like 'Connect your wallet'.
Watch the demo
What it does
A developer and analytics tool that maps app workflows from source code, identifies untracked steps and combines log analysis with targeted exit questions to explain user drop-off. Built with TypeScript, React, Python, FastAPI and SQLite, using DeepSeek, packaged with Docker and deployed on Railway.
Try it yourself
U-tags
Tap a tag to find similar projects
Meet the team
This is an independent hackathon project. Some features may be prototypes. Please do your own research before relying on it.