Our decision on Claude

Co-sign. This is one of the key aspects that will emerge in best practises for how these systems are eventually designed. This is just shilling for the Warp terminal, and this approach could have been a huge accelerator, kind of like where we are now.

How rigorous is your code review process when using agentic tools? Do you mandate that folks responsible for the functionality should be fully aware of the code which the agent failed to detect. Can anyone convince me why I did something. It also helps with the invalidation. How is the invalidation handled in Warp? Is it actually all just fake?