We built an AI document processing system for Deutsche Verrechnungsstelle AG — one of Germany's largest billing/factoring companies.
2M+ documents processed in the first month. Fully GDPR-compliant. Two-person team from Berlin.
Full case study:
@garrytan How do you make sure that the models actually are reading the docs and using web search and are successfully researching before implementing?
That's the biggest problem I have. They're always building their own solutions and workarounds and not using the official documentation
genuinely fuck whoever came up w the dumbass idea to replace THE DICTIONARY BUILT INTO GOOGLE with the ai overview's definitions i hope everything in their life fucking sucks
genuinely fuck whoever came up w the dumbass idea to replace THE DICTIONARY BUILT INTO GOOGLE with the ai overview's definitions i hope everything in their life fucking sucks