01 · Local AI · evaluation
PromiseDiff

A local AI reviewer for the awkward moment when a polished product listing and the file that arrived may not be telling the same story.
It separates directly measured facts from LLM interpretation — and leaves uncertain claims unverified.
- Built with
- React · FastAPI · PDF/ZIP inspection · Ollama / Gemma
- Honest boundary
- Small public benchmark, synthetic cases only. Useful as an evaluation scaffold, not an accuracy claim.

