Small decisions. Interesting possibilities.Submit contentSubmit

How it uses Jev

For a single voice command, local speech recognition produces an utterance; Jev receives that text, the frontmost app, installed-app candidates, and code-cut text candidates with a fan-out of typed questions. It selects action and argument candidates; code executes locally. Multi-step screen tasks use a separate one-request-per-step accessibility/browser loop.

What Jev decides

Voice intent requestExample answers · not a recorded Jev response · Source ↗
Question 1 · addressed
YOUR APP
INSTRUCTION

Is this utterance a direct command to the computer?

STATE

The utterance transcript and candidate apps, sites, and actions are included in state. This chart shows fixed Noul questions from the single speculative request.

JEV · NOUL
YesNo
Question 2 · compound
YOUR APP
INSTRUCTION

Does it request two or more actions in sequence?

STATE

The utterance transcript and candidate apps, sites, and actions are included in state. This chart shows fixed Noul questions from the single speculative request.

JEV · NOUL
YesNo

App workflow

  1. Capture and transcribe

    Energy-based voice detection gates local whisper.cpp transcription; wake-word and follow-up modes decide whether to route the utterance.

  2. Build typed candidates

    The command brain discovers installed apps and cuts possible text payloads from the utterance, then assembles action and argument questions.

  3. Select and execute

    Jev chooses from the candidates; code maps the answer to a macOS action. Multi-step tasks observe an accessibility/browser tree and ask Jev for a bounded next step.

  4. Report the run

    The app records decisions and actions, supports dry-run for typed routing, and can speak a response.

Why it is interesting

The single-command path resolves action, arguments, and intent gates in one request while keeping candidate creation and execution in code. Screen tasks instead use observed indexed controls; Jev does not receive screenshots.