Product
A user signed in with Google, picked a subject and typed a problem into the chat or uploaded a photo. Tesseract OCR read the text from the photo. The answer came step by step, and KaTeX rendered the formulas.
AI problem solver · 2026
StuddyGo
StuddyGo helped school and university students with math. It explained the solution step by step instead of only giving the answer. I made it with the same partner as Getvibemotion.
Subscriptions and limits
A few problems a day were free, after that you needed a Stripe subscription. Daily limits were counted in Redis, so the database didn’t get a hit on every request.
Architecture
Front end on Nuxt 4 and Nuxt UI with SSR, back end on NestJS 11 and Prisma, PostgreSQL. The model is connected through a separate layer, so it can be replaced. Chats and messages used soft delete, and requests were rate limited. Everything ran with Docker Compose.
Outcome
We got the product to a working state, then closed the project.
Results
Step-by-step solutions and KaTeX formulasProblems from a photo through OCRSubscriptions and daily limitsProject closed
Need to launch a product?
Send me the idea, the repo or the unfinished project. First I’ll ask questions, then I’ll send a written scope. Looking for someone to join your team? Tell me which role.