korrents

korrents · video

Cursor: coding agents tutorial (2026)

Lee Robinson · 31m · youtube.com ↗

18 korrents from this recording

Lee Robinson 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. 1:49 · watch on youtube.com↗

    but it's important to note that the intent you provide the models through prompting really makes a difference in the quality that you get out.
  2. 2:14 · watch on youtube.com↗

    And I typically recommend if you're starting a new feature, you should probably start a new conversation with the agent. Or if you see the agent kind of going off track and making mistakes, that's also a good sign to start a new conversation.
  3. 1 min later
  4. 3:06 · watch on youtube.com↗

    One of the most important jobs of a software engineer is to build a mental map of a code base and to deeply understand how the system works.
  5. 3 min later
  6. 5:49 · watch on youtube.com↗

    if you're searching through a very large code base with many files, it's going to generate a lot of context usage and a lot of tokens. So, I highly recommend using sub agents to improve your context management.
  7. 1 min later
  8. 6:21 · watch on youtube.com↗

    A common mistake I see all the time is when developers ask the agents to change code, but they don't really understand exactly how that code works yet.
  9. 6:46 · watch on youtube.com↗

    And sometimes that might work, but it's really important to follow the existing patterns in your code base, otherwise you can create a lot of tech debt.
  10. 1 min later
  11. 7:22 · watch on youtube.com↗

    And the key to doing this effectively with coding agents is to break the work into steps that the agent can verify on its own. So, I recommend starting every new feature with a plan and then setting up the right guardrails so the agent can verify and fix its own mistakes.
  12. 7 min later
  13. 14:03 · watch on youtube.com↗

    And even with help from coding agents, it's worth brushing up on the fundamentals of how to do effective debugging. Great debugging follows the same principles whether a human or an agent is doing the work.
  14. 3 min later
  15. 16:35 · watch on youtube.com↗

    So, first, you can ask multiple models to fix the same bug, and then you can compare the results. Every model can take a somewhat different approach, and when you have multiple shots on goal, you can then pick the best option out of the few.
  16. 1 min later
  17. 17:33 · watch on youtube.com↗

    But by far, my biggest tip is to make sure you really understand the proposed solution. If you don't understand the fix, it's going to be very hard for you to validate whether the code is actually correct.
  18. 1 min later
  19. 18:35 · watch on youtube.com↗

    Coding agents can write a lot of code, which means they can also produce tech debt or introduce an accidental bug. Your standards for what gets merged should be the same whether it was written by an agent or written by hand.
  20. 18:48 · watch on youtube.com↗

    This AI-generated code can look correct, but just be slightly wrong. It might follow all your existing patterns, compile, pass test, yet still have an issue somewhere in your code base. This is why code review is so, so important.
  21. 2 min later
  22. 20:18 · watch on youtube.com↗

    I find that when you break it down into more semantic commits, it's much easier for a human reviewer to step through the commits and understand things if they have more questions.
  23. 2 min later
  24. 22:18 · watch on youtube.com↗

    But, I found that agents make writing tests much more approachable when you can ask the agent not only to write the test for a new feature, but also verify that they're correct.
  25. 2 min later
  26. 24:06 · watch on youtube.com↗

    agents, you can only move as fast as the slowest part of your system. And that's often waiting for a test suite to finish or running type or lint checks across your entire code base or other steps in your CI pipeline.
  27. 2 min later
  28. 25:59 · watch on youtube.com↗

    A great rules file is short, it's specific, and it points to examples in your code base that you want the agent to reference.
  29. 26:25 · watch on youtube.com↗

    Now, you might be tempted to write rules for everything, but you should really resist this. Too many rules will consume just an unnecessary amount of context, and it might honestly confuse the agent.
  30. 5 min later
  31. 31:11 · watch on youtube.com↗

    The tools and the models are improving so rapidly that all of the specifics will change over time, but this core skill that you're learning of how to work with a coding agent is quickly becoming one of the most important parts of software engineering.