I think this is a great feature, but it's still at the MVP stage. As a UX designer, I'd suggest that Anthropic develop more options for providing feedback on the model’s actions.

- Right now, I can only accept or reject the suggested response. Adding or editing it requires a lot of steps.

- It would be great to have a neat autocomplete feature. That's because prompts always need to be detailed, and that means typing a lot of text that’s essentially already in the context (and that's exactly what we should be using).

- It would be better to have a menu with action options and not have to type anything at all. Previously, Claude did a good job displaying a UI with different options (but for some reason, it stopped working for me specifically - probably because I specify everything in as much detail as possible).

- Again, providing details means the user explicitly agrees to the conditions, and the prompt is more effective on every level—plus, it caches better. Otherwise, users usually write something like: "Do everything, but switch the left one to the right and flip the one on the far end twice" (in response to three blocks of lists with task IDs) - even other people wouldn’t understand that.