Finally, make sure Claude has a way to verify its work. This has always been important — now 4.7 is 2-3x what you get out of Claude, so it's more important than ever.
Verification looks different depending on the task:
- Backend work — have Claude run your server/service to test end-to-end
- Frontend work — use the Claude Chromium extension to give Claude a way to control your browser
- Desktop apps — use Computer Use
Boris's prompts these days look like Claude do blah blah /go, where /go is a skill that:
- Tests itself end-to-end using bash, browser, or computer use
- Runs
/simplify - Puts up a PR
For long-running work, verification matters even more — when you come back to a task, you know the code works.