Let Your Agents Review, But Look Before Humans Do
Agents can run multiple rounds of review and verification before you look. But ship to humans without looking yourself, and something subtle always feels off — because fully specifying a system that feels right to a human is hard.
Some interesting thoughts in Noah Smith's piece, "Your future job will be to keep AI on task."
I've had a lot of luck letting different agents do multiple rounds of review and verification before I look at things — but I've regretted it when I don't look at things at all before other humans use the system I'm working on, even with clear acceptance criteria checked off explicitly.
There's always something in the details that is a little off, mostly because it's hard to completely specify a system that feels right to a human, at least while humans are the target user. There's lots of software where agents are the target user and that's a different story. Even then, the agents are still working on behalf of something humans want.
Related insights
Deep Work vs. the Agent Badge
The most productive use of my time is often putting the agents on do not disturb — but that red notification badge keeps paying out little dopamine hits.
You're Going to Need to Ship a Fix in Minutes, Not Days
Agents are making it cheap for attackers to find unlocked doors. The window to invest in CI, test coverage, and fast safe rollback is now.
Agents Are Going Multi-Player
Most people's experience with AI agents is single-player. We're moving into a multi-player era where specialized agents live in your team channels as true teammates.
Get More Like This
Follow along as I build and share what I learn
Found this helpful? Share it with your network!