Comment by ZitchDog
3 days ago
I've created my own "claw" running in fly.io with a pattern that seems to work well. I have MCP tools for actions that I want to ensure human-in-the loop - email sending, slack message sending, etc. I call these "activities". The only way for my claw to execute these commands is to create an activity which generates a link with the summary of the acitvity for me to approve.
Is there a risk that the summary doesn't fully match the action that actually gets executed?
Side note: Just like with a human employee asking for permission to do something.
Except for the accountability if they screw up; and the human brain thinking through what they are doing.
The approval-link pattern for gating dangerous actions is something I keep coming back to as well, way more robust than trying to teach the agent what's "safe" vs not. How do you handle the case where the agent needs the result of the gated action to continue its chain? Does it block and wait, or does it park the whole task? The suspend/resume problem is where most of these setups get messy in my experience.
Any chance you have a repo to share?