Connect an AI model

Adhoc Kit runs your text tools and file edits by sending prompts to an AI model. You choose the provider, test the connection, and review every change before it happens.

Choose your model

Cloud AI provider

Connect a standard API endpoint to use a cloud model. Your prompts and file text go to that provider.

Local PC model

Run a model directly on your Windows machine. Nothing leaves your computer when you use this mode.

Built-in model

Use the built-in model that comes with the app. It is ready to use without your own endpoint.

Test your connection

Click the Test button to check your endpoint. The app shows the response time and the context window size. This confirms that the endpoint answers.

Pick the right model

Use a bigger model for complex refactors and logic. Use a smaller model for simple edits and quick tasks. You can use run_on_model to send a hard step to a bigger model when needed.

Quality varies between models and tasks. Always review the diff before accepting changes. Use Ask first to pause before actions that change something. This ensures you stay in control of every edit.