# AI use cases for Jev Use (savka777/jev-use)

Repo: [savka777/jev-use](https://github.com/savka777/jev-use) | Use cases: 4 | Page: https://dedupedai.com/use-cases/savka777-jev-use/

jev-use is a macOS app that takes a spoken or typed command, reads the front app through the Accessibility tree, and performs the next on-screen action with no screenshots.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run Mac actions by voice without a screenshot: https://dedupedai.com/use-cases/savka777-jev-use/run-mac-actions-by-voice/
- Control the Mac hands-free with a wake phrase: https://dedupedai.com/use-cases/savka777-jev-use/control-mac-hands-free-with-wake-phrase/
- Tile windows or repeat a task in every window: https://dedupedai.com/use-cases/savka777-jev-use/repeat-a-task-across-app-windows/
- Let a coding agent drive the Mac from a shell command: https://dedupedai.com/use-cases/savka777-jev-use/let-an-agent-drive-the-mac-from-shell/

## How to run Mac actions by voice without a screenshot with Jev Use

Repo: [savka777/jev-use](https://github.com/savka777/jev-use) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Hold a shortcut, say a command, and Jev performs the matching action in the front app.

**Who it is for:** A Mac user who wants to open apps, use menu items or type text by speaking, without clicking through menus.

**The problem:** Doing routine steps across many apps means repeated clicking and menu hunting.

**The outcome:** Spoken or typed commands such as opening an app or choosing a menu item are carried out on screen.

### Steps

1. Quit Jev Use if it is running, then run `bash build.sh` in the repo folder.
2. Run `open "$HOME/Applications/Desktop Voice.app"`.
3. In setup, save your TypeSafe API key, then allow Accessibility, microphone and speech.
4. Hold Control-Option-Space, say a command such as "Open Finder", then release.
5. Check the screen for the result; press Escape to cancel a recording.

### Prompt to paste into your agent

```text
Using the jev-use repo on this Mac, run `scripts/say.sh "<command>"` with the command text in place of <command>, for example "Open Finder". Expect the app to perform the action and report DONE, BLOCKED or WAIT. Verify by running `log show --predicate 'subsystem == "local.jev-use"' --last 10m --info` and confirming the logged result matches the expected action.
```

### Caveat

Voice recognition uses Apple Speech, which may process audio online, and command context is sent to TypeSafe.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/savka777-jev-use/run-mac-actions-by-voice/

## How to control the Mac hands-free with a wake phrase with Jev Use

Repo: [savka777/jev-use](https://github.com/savka777/jev-use) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Enable the "Hey Jev" wake phrase so commands start by voice with no widget click.

**Who it is for:** A Mac user who wants to give commands by voice and keep the keyboard and mouse free.

**The problem:** Starting each voice command needs a click or key press, which breaks flow when hands are busy.

**The outcome:** Saying "Hey Jev" followed by a command opens the widget and carries out the command.

### Steps

1. Run `bash build.sh` with the app quit, then run `open "$HOME/Applications/Desktop Voice.app"`.
2. Complete setup and grant Accessibility, microphone and speech permissions.
3. In Settings, enable Invoke the widget by saying “Hey Jev”.
4. Say "Hey Jev, open Finder" and wait for the action to run.
5. Press Escape or click Stop to pause all listening; use Resume wake-word listening in the menu bar to restart it.

### Prompt to paste into your agent

```text
On this Mac, use the jev-use app with the wake phrase enabled in Settings, then say "Hey Jev, <command>" with the command in place of <command>. Expect the widget to appear and the command to run, then listening to return to background wake-word mode. Verify the outcome on screen and confirm the wake phrase is still active in Settings.
```

### Caveat

Wake-word listening is not a dedicated offline engine and uses Apple Speech, which may process audio online.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/savka777-jev-use/control-mac-hands-free-with-wake-phrase/

## How to tile windows or repeat a task in every window with Jev Use

Repo: [savka777/jev-use](https://github.com/savka777/jev-use) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Give one command that arranges windows or runs the same steps in each open window.

**Who it is for:** A Mac user with several windows open in one app, such as a browser, who needs the same task done in each.

**The problem:** Repeating the same steps in every window by hand is slow and easy to get wrong.

**The outcome:** Windows are tiled so none are stacked, or a task such as a search runs once in each window.

### Steps

1. Run `bash build.sh` with the app quit, then run `open "$HOME/Applications/Desktop Voice.app"`.
2. Complete setup and grant the required permissions.
3. Say "Tile all the Brave windows so none are stacked" to arrange the windows.
4. Say "In every Brave window, go to wikipedia.org and search for accessibility" to repeat the task.
5. Review each window, since Jev asks before acting on low-confidence or destructive picks.

### Prompt to paste into your agent

```text
Using jev-use on this Mac, run `scripts/say.sh "<command>"` where <command> is a window task for the app <app>, such as tiling its windows. Expect the windows to be arranged or the task repeated in each window, with the result reported as DONE, BLOCKED or WAIT. Verify by checking every window on screen and reading the log with `log show --predicate 'subsystem == "local.jev-use"' --last 10m --info`.
```

### Caveat

The README does not state how Jev handles every window layout, so check each window after a command runs.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/savka777-jev-use/repeat-a-task-across-app-windows/

## How to let a coding agent drive the Mac from a shell command with Jev Use

Repo: [savka777/jev-use](https://github.com/savka777/jev-use) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Call scripts/say.sh so an agent can open apps and use menus on the Mac.

**Who it is for:** A developer whose AI agent needs to act on desktop apps, such as opening an app or choosing a menu item, as part of a larger task.

**The problem:** Agents cannot act on the desktop apps a developer uses, so each step needs manual work.

**The outcome:** An agent sends a typed command through the shell and the Mac performs it, with the result logged.

### Steps

1. Run `bash build.sh` with the app quit, then run `open "$HOME/Applications/Desktop Voice.app"`.
2. Complete setup, including the TypeSafe API key stored in the Keychain and the Accessibility permission.
3. Run `scripts/say.sh "Open Finder"` to confirm the shell path works.
4. Have the agent call `scripts/say.sh` with each command it needs.
5. Check the result with `log show --predicate 'subsystem == "local.jev-use"' --last 10m --info`.

### Prompt to paste into your agent

```text
In the jev-use repo on this Mac, run `scripts/say.sh "<command>"` where <command> is the desktop action to perform, such as "Open Finder". Expect the Mac to perform the action and the app to report DONE, BLOCKED or WAIT. Verify by running the log command above and confirming the logged effect matches the requested action.
```

### Caveat

Each command sends your command, app and window names, and on-screen labels and values to TypeSafe, so do not point an agent at sensitive screens.

Risk, credentials: The TypeSafe API key is stored in the Keychain, and an agent that runs commands acts with your Mac permissions, so limit which commands it sends.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/savka777-jev-use/let-an-agent-drive-the-mac-from-shell/
