All blogs
A voice agent that browses the web for people who cannot use a screen
Speak a task, and an agent drives a real browser and talks the results back. Built with safety limits and an audit log for caregivers.
- Client
- h1902y
- Year
- 2026
- Status
- Experiment
- Timeline
- July 2026
The problem
Blind, low-vision and cognitive-disability users need to get things done on the web without a screen or an install.
What we built
- A voice-first web channel with a browser speech client and a session state machine, including stop words and spoken confirmation
- A safety layer: blocked categories, actions that need confirmation, and rules per domain
- Usage caps per user and overall, and an append-only audit log for caregivers
- An agent runner that drives a real browser, plus a phone channel skeleton
Stack
- Python
- FastAPI
- Playwright
- browser-use
- WebSockets
Where it landed
- Working on localhost; not deployed
- Open risks are written down: browser isolation, privacy and prompt injection
Want something like this?
Tell us the idea in a few lines. We will say what week one looks like.
