endyai

isn't that his point?

so does an app

"When Agent A writes code in one file that breaks Agent B's assumptions in another file."

Each agent runs in a separate worktree or cloned copy of the repo, independently. When the task is done, a PR is opened. The issue you mentioned gets caught during merge conflicts.

No different than a "real" dev team?

You can handle this in a few ways depending on the task. Even. adding to the prompt "double check your answer before answering" - the agent will take another turn to double check its work. You can also do this with a fresh task/prompt.

Ideally, if you are able to use code to validate (either with a test or eval) that works best.

25% of all EV sales though