Real Alpha
Try Pro free

The Pragmatic Engineer · 3 min · Jan 28, 2026

AI makes upfront planning cheaper to revise, not unnecessary

Peter Steinberger · Creator, OpenClaw

He still plans, but invests less before trying a shape because changes cost less.

In this episode

Full analysis
  1. 57:20Agents work best when they can test and debug their own output6 min
  2. 1:03:37A single prompt is a poor test of AI coding4 min
  3. 1:34:18AI adoption requires redesigning teams and codebases4 min
  4. 42:58Codex trades speed for stronger context on complex apps6 min
  5. 1:21:43CLIs let agents filter and chain tool calls3 min
  6. 1:11:03AI makes upfront planning cheaper to revise, not unnecessary3 min
  7. 24:03A 50,000-page PDF forced a two-month redesign2 min
  8. 29:29Burnout came from lost belief and conflict, not just long hours4 min
“but I don't put as much into it because it's not so much easier to just like try and look at the results”
Peter Steinbergerat 1:11:34 · The Pragmatic Engineer
1:11:34

Takeaways

  1. He plans less upfront, then learns from trying a prototype.
  2. Building reveals requirements that are hard to know in advance.
  3. Codex handled a multi-provider change in three hours.

About this segment

He still plans, but invests less before trying a shape because changes cost less. A multi-provider rewrite took Codex three hours, versus his estimate of two weeks by hand.

Peter Steinberger

Peter Steinberger is creator of OpenClaw and founder of PSPDFKit.

Created viral open-source personal agent OpenClaw and joined OpenAI to drive next-generation personal agents.

  • Gergely Orosz, Host · Host, The Pragmatic Engineer

    Spent four years at Uber heading mobile, web and backend teams; shipped part of its payments system.

From “The creator of OpenClaw: "I ship code I don't read"”, Jan 28, 2026. Watch the full episode

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 1:11:09

    this seems like a change because before we had AI or any of these agents, upfront planning did make a difference. You know, writing, at PSPDF, you insisted I think to have a proposal where people put a lot of thought up front to specify and do because it was expensive to I guess to build do you think this is changing because of the cost of just writing code is going down or I still plan you still do yes but I don't put as much into it because it's not so much easier to just like try and look at the results and then see if oh yeah this this shape could work or no we have to like the tweaking and even even like oh no we have to like do it a completely different way it's not so much cheaper that it's to me it became much more playful Yeah, I guess because like, you know, when you're working, even if you have like a new grad on the team or an intern, you know, you give them something, they're working for a day or two.

  2. 1:12:07

    Now you give them another, it's not a day or two, you know, and we're not talking days here, we're talking minutes or like if it's a long running task, like 10, 20 minutes at worst. Plus, you're not just waiting on that thing, you have parallel things running. So it's not that much of a waste, if you will. In Cloud, but at the beginning, I had this assumption of like one agent and then eventually changed to multiple agents.

  3. 1:12:30

    and there was an assumption of like one provider like whatsapp and now it's multiple ones and changing that was like such a pain would i would have been such a pain if i would have written it myself because you have to weave in literally everything through the whole logic of the application and yeah it took codex like three hours it would have taken me like two weeks you know so so that upfront planning i i could have realized it in the beginning but now i i I know that I can just change things and it's much easier to work down your technical depth or you evolve how you think about a project as you build a project.

  4. 1:13:08

    That's why I don't believe in, I don't know, things like Gastown where you write up this back and then it builds itself and then it's done. How can you even know what you want to build before you built it? You learn so much in the process of building it that will go back into your thinking of how the system actually will end up being. To me, this is very much a circle until I... You don't walk up the mountain like this.

  5. 1:13:32

    You go around and sometimes you like you stray off a little bit of paths, but eventually you reach the top. That's how I feel it's Australia.