← Presentation home · Part 2 of 4
Problem we are solving
- Clinic I work in: policies and procedures, answers needed now
- A stock internet AI still answers, and it makes mistakes, because it does not have our docs
- RAG (retrieval-augmented generation) cuts those mistakes down hard. Set it up right and you practically get none
- You can do this RAG stuff in Claude. It works. It is still public, and you may not want that out there
- We wanted the model and the files on hardware we own