Connect an AI model for CTF practice

Choose how the agent talks to a language model. You can use a cloud provider, a local model on your PC, or the built-in model. Each option changes privacy and speed.

Three ways to connect a model

Cloud API provider

Connect a cloud AI provider through a standard API endpoint. The prompt and file text go to that provider, so data leaves your machine.

Local model on your PC

Run a model locally on your PC using your own hardware. Nothing leaves the machine when you use this option, keeping all secrets and notes private. This suits beginners who want full control over their data and do not want to send context to a third party. It may be slower.

Built-in model

Use the built-in model that is ready to use without your own endpoint. You can switch to a cloud provider later.

Test your connection

Press the Test button to check an endpoint. It shows response time and the context window. This helps you verify that the model is reachable and fast enough for your workflow before you begin solving challenges.

Pick the right model for the task

Send a hard step to a bigger model using run_on_model. Use a smaller model for small edits and simple file changes. This balances speed and quality. You can switch models for specific tasks to get better results for complex logic.

Quality varies between models, so review the diff. Use Ask first to pause before actions that change something. Check the output carefully before you accept the changes. This keeps you in control of your lab and notes.