ui-insight/vandalizer ? reverse-engineered prompt

Reverse engineered prompt

Build me a self hosted web app for research administration teams that can upload grant and compliance documents, extract key details like deadlines, budgets, requirements, and PI info, and organize everything into project workspaces. I want staff to be able to ask questions in plain English about their documents and get answers with citations back to the source files.

It should support repeatable extraction workflows, basic validation against test cases, team collaboration with shared access, and an admin area for setting things like branding, logos, and email details. Make it work with any OpenAI compatible model, including local models if possible, and keep the whole thing private so it can run on our own infrastructure.

Please build the frontend and backend, wire up the database and storage, and make it easy to start locally with Docker. If you need to check current docs for the libraries or model APIs, look them up online first.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab