Connect an AI model for your Windows checks
DevHolic Studio works with a cloud AI provider through a standard API endpoint, a model running locally on your PC, or the built-in model. You pick the provider, test the connection, and decide how much data leaves your machine during each investigation step.
Choose your model source
Cloud AI provider
Send prompts to a cloud AI provider through a standard API endpoint. Your text and file contents travel to that provider, so you must trust their privacy policy.
Local PC model
Run a model directly on your Windows 10 or 11 machine. No prompt text leaves the PC with a local model. This approach uses your local hardware, so performance depends on your available RAM and processor speed during the check.
Built-in model
Use the built-in model included with the software.
Verify your connection settings
Press the Test button to check an endpoint. The interface shows the response time and displays the context window size.
Select the right model size
Use a bigger model for complex log analysis or intricate logic tasks. Send a hard step to a bigger model using the run_on_model feature.
Model quality varies between providers and versions. Always review the diff before accepting changes. Use Ask first mode to pause before actions that change something.