All work — Machine learning — 2026

Jarvis Wake

Always-on desktop assistant listening for a wake phrase, then routing the spoken task straight into Gemini.

Runs natively — not a browser app Ask me about this

The problem

Voice assistants require a click before they can hear you.

How I approached it

A continuous listener watches for the wake phrase and handles both patterns — wake word and task spoken together, or the task arriving as follow-up speech.

The outcome

Hands-free task dispatch from anywhere on the desktop.

Jarvis Wake

Next project

Screen Solver →

Need something
like this?

This is the kind of problem I take on. Tell me about yours.