Choose your AI model

Choose a cloud API, a local Windows model, or the built-in option. Test the endpoint to see response time and context window before starting.

Pick your model

Cloud AI provider

Use a cloud AI provider through a standard API endpoint. Your prompts go to that provider, so file text leaves your machine. This suits heavy reasoning tasks when you do not mind the data traveling over the network to complete complex configuration reviews.

Local PC model

Run a model directly on your Windows PC. Nothing leaves the machine when you use this option. Keep your secrets and configuration files entirely on your hardware, which is ideal for sensitive load balancer setups that require strict privacy during the review process.

Built-in model

A model running locally on your PC.

Check your connection

Press the Test button to verify your chosen endpoint. The tool shows the response time and the context window.

Select the right size

Send a hard step to a bigger model using run_on_model.

Quality varies between models, so review the diff. Use Ask first to pause before every action that changes something. Check the file diff carefully. Accept the changes only when you are satisfied with the proposed configuration updates for your servers.