Do you even need human review?

Matt Pocock · 2026-07-20 · 1 min · 25 sentences · from YouTube's caption track

Each timecode opens YouTube at the start of that sentence. Line anchors (#s42) are the cue ids in the WebVTT, and every line carries its start and end seconds. All transcripts has every talk, and the whole corpus as one file.

  1. 00:00Everyone's obsessed with automating work with engineers.
  2. 00:02And the way you do it best is to figure out where you need human review.
  3. 00:07Let's say you have a process that looks like this.
  4. 00:09Imagine totally pre-AI where maybe you plan some work and then you ship some work and then maybe you review some work.
  5. 00:17And all of these checkpoints, all of the moments where you check the work, these are all human.
  6. 00:22A lot of people's dream, I think, is to have these all translated over to AI at once.
  7. 00:27But for me, that doesn't really make sense.
  8. 00:29On very large pieces of work, you probably want to align with the AI first.
  9. 00:33In other words, you want to be involved at the initial planning stage.
  10. 00:37That's what my skills like Grill Me and Grill with Docs and Wayfinder all do.
  11. 00:40And then you probably also want some human review right at the end before you ship it to production.
  12. 00:45However, there are some situations where you don't need that much human review at the end because maybe it's just a refactor, just an internal documentation rename.
  13. 00:53Maybe the human can just align early on, basically consider that the plan is done, and then the AI can ship it all the way to prod.
  14. 01:00That is good for some cases.
  15. 01:02There are also some cases where you can just specify the work that needs doing in like a single prompt, not bother really aligning with the AI, not bother grilling,
  16. 01:09and just let it ship through the process, and then just review it before it goes live.
  17. 01:14That can be really effective for very simple changes, very small diffs, stuff that's not going to make a big splash or a big impact, you know, just changing the color of a button or changing the name of a title or something.
  18. 01:24Even things like fix a small bug here that's just a couple of lines change, you should probably shift that checkpoint to the right.
  19. 01:31And that's the right language to use here.
  20. 01:33You shift checkpoints left for big work, for stuff you need to align on first, and you can shift it to the right for small work.
  21. 01:40The reason for that is that the smaller the diff, the easier it is to totally regenerate the code and hold it all in context.
  22. 01:46So, if you have really massive work, you want to align beforehand because fixing it is really expensive when you get to a later stage.
  23. 01:53So, that's the theory.
  24. 01:54For big work, you shift the review left.
  25. 01:56For small work, you shift the review right.