Curious, does it connect to my claude code, or ChatGPT automatically and constantly inject some kind of context in it. Or do you have to connect to some kind of a MCP.
You are correct. In the onboarding process we install hooks to your machine (and also give an MCP option for unsupported agents that don't have a hook protocol). We do this because MCP is inherently unreliable -- you are at the whim of the calling agent to recognize the connection between the tool call description and the user's query. Hooks let you reliably run side effects as part of the lifecycle. All of this is configurable from our desktop UI.