Simple backend for product-market fit interviews. One flow, one service, no complexity.

# Create virtual environment
python3 -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Run the server
uvicorn main:app --reload --port 8000

Once running, visit: http://localhost:8000/docs

POST /start

{
  "product": "A SaaS platform that helps you create your own customized AI experiences"
}

Returns: session_id + 3 initial interview questions

POST /live/start

{
  "session_id": "123"
}

Returns: { "status": "live" }

POST /live/transcript

{
  "session_id": "123",
  "text": "We usually hack something together with prompts."
}

Returns: 2 AI-suggested follow-up questions

POST /live/stop

{
  "session_id": "123"
}

Returns: { "status": "stopped" }

GET /analysis?session_id=123

Returns: Structured rows with question, answer, and category

POST /report

{
  "session_id": "123"
}

Returns: Summary, key pain points, and opportunities

Create a .env file:

yutori=your_api_key_here

• In-memory session storage (no database required)
• Yutori API for LLM calls
• FastAPI for the web framework

Input → LLM → Store → Return

That's it. Simple.