Building Two SaaS MVPs with AI: What I Learned

Building Two SaaS MVPs with AI 🤖

Hello! I wanted to share two products I built with the help of AI. It was a valuable learning experience, and I enjoyed the process from start to finish.

🛠️ Tech stack

Both projects use a similar stack:

• Backend: Python and FastAPI
• Frontend: React, TypeScript, and Vite
• Database: PostgreSQL
• Caching: Redis
• Development and deployment: Docker and Docker Compose

The most rewarding part was learning how to take an idea from scratch and turn it into a working SaaS MVP. The projects aren’t perfect, and there’s still room to improve them, but both are up and running.

📄 AI Document Platform

An AI-powered document search and Q&A tool. It creates embeddings using OpenAI or local models, then answers questions based on the uploaded documents.

Explore the AI Document Platform repository.

💻 AI Code Evaluation Platform

A tool for evaluating AI models’ code-generation results using prompts and tests you create. It’s mainly an evaluation platform for AI, rather than necessarily an AI model itself.

Explore the AI Code Evaluation Platform repository.

🚀 Running the projects

You’ll need Docker and Make installed. I’ve automated much of the setup, so you can try starting the projects with:

bash
docker compose up