korrents

korrents · video

How I to Put My Codebase on Autopilot

Kent C. Dodds · 19m · youtube.com ↗

12 korrents from this recording

Kent C. Dodds did not write this page.

Every claim below is a statement made in this recording, quoted word for word and linked to the second it was said, so you can hear it rather than take our word for it. The wording comes from the transcript published alongside the recording; the sentence above each quote is our reading of the claim, not their wording.

  1. 1:22 · watch on youtube.com↗

    But it compounds and it explodes in how much friction you actually end up feeling when you've got so many agents who are discovering this work around when in reality you really just want to have those things fixed. And so what you need is to turn your agents into complainers.
  2. 1 min later
  3. 2:30 · watch on youtube.com↗

    And I'm telling you that this really greases the wheel of your software factory or your repository to make agents more effective and efficient in the codebase because they discover all kinds of things.
  4. 1 min later
  5. 3:36 · watch on youtube.com↗

    So of course I'm going to be involved in the product decisions and and the product direction and all of that. I'm still the bottleneck there and I actually feel like it should continue to be that way.
  6. 4 min later
  7. 7:28 · watch on youtube.com↗

    The same sort of thing that we have done as engineers over the years as we make a change, and we go to the browser and click around and whatever. And agents are good enough that they can do that now.
  8. 2 min later
  9. 9:09 · watch on youtube.com↗

    Where this becomes valuable is it forces the agent to really think about what primitives it put together and make sure that those primitives all piece together in a sensible way.
  10. 1 min later
  11. 10:29 · watch on youtube.com↗

    after review, I think if I could only have one, then I would keep the the Cursor BugBot one because it seems to have caught more problems.
  12. 2 min later
  13. 12:41 · watch on youtube.com↗

    So, for big experiments or things that I'm not sure I want to commit to or whatever, we're going to stick that behind a feature flag. And an agent can decide to create a feature flag itself.
  14. 1 min later
  15. 13:51 · watch on youtube.com↗

    And so, you absolutely have to have a disaster recovery story for your application. It just becomes so much more important the bigger your application gets, and the more people are who are working on it.
  16. 1 min later
  17. 14:34 · watch on youtube.com↗

    But, agents love to create code, and they don't love to delete code. And so, you have to be a little bit intentional about making sure that they go through and clean things up.
  18. 1 min later
  19. 15:28 · watch on youtube.com↗

    Dog fooding is another really valuable thing that you have your agents do. Get your agents to use your software somehow because in the process of using the software, they're going to find friction and they'll log that as friction as well.
  20. 1 min later
  21. 16:09 · watch on youtube.com↗

    I'm letting it make the decisions for like how things are constructed and put together, implementation details, but the product vision still belongs to me.
  22. 16:36 · watch on youtube.com↗

    You do just need to find a whole bunch of ways that input like useful signal can come into your system and then your agents can work on that and then flag things that you need to look at, but try to get yourself out of the picture.