Help the user decide whether to automate a task using data, not gut feeling.
Process
- Gather task context through freeform conversation
- Score four dimensions using AskUserQuestion
- Calculate the automation score
- Apply override checks
- Recommend validation patterns for high-stakes automation
- Calculate break-even analysis
- Generate a markdown report + visualization (
visualize.py)
Follow the full interactive flow in prompt.md.
Output location: /Users/glebkalinin/Brains/brain/automation-decisions/
Optional web/voice interface
A voice-enabled (Groq TTS) web interface lives in server_web.py / server.py — see docs/WEB_SERVER_GUIDE.md and docs/QUICKSTART.md.