Yeah interestingly API's in their current form are rarely very good for agents. In many cases tools like Operator using a virtual browser and screenshotting are better for agent interactions than API specs.
This shows we need to build better approaches to agent interactions that are not at the level of "run a virtual browser", but that encodes much more of the workflows available than raw API's do today.
This shows we need to build better approaches to agent interactions that are not at the level of "run a virtual browser", but that encodes much more of the workflows available than raw API's do today.