Real Alpha
Watch modeSubscribed

Training Data · 2 min · Apr 29, 2026

Agent-first services should let agents handle setup and deployment

Andrej Karpathy says today’s docs and cloud setup still assume a human operator. He sees agent-readable infrastructure—and agents representing people and organizations—as the next step.

Andrej Karpathy

Andrej Karpathy is co-founder of OpenAI, former head of AI at Tesla, and founder of Eureka Labs.

Joined Anthropic's pretraining team; founded Eureka Labs, an AI-native school, after leading Tesla's Autopilot AI.

  • SZ

    Stephanie Zhan, Host · Partner, Sequoia

About this segment

Andrej Karpathy says today’s docs and cloud setup still assume a human operator. He sees agent-readable infrastructure—and agents representing people and organizations—as the next step.

From “Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan”, Apr 29, 2026. Watch the full episode

“What is the thing I should copy paste to my agent?”
Andrej Karpathyat 25:54 · Training Data25:54

Takeaways

  1. Most documentation and setup still target humans.
  2. Deployment across services can be harder than writing the code.
  3. Karpathy expects agents to represent people and organizations.

In this episode

Full episode
  1. 2:24Software 3.0 makes some apps unnecessary5:13
  2. 9:29Verifiability helps explain where AI excels4:11
  3. 19:22Engineers still need to own judgment and system design4:15
  4. 15:42Agentic engineering raises output without lowering the quality bar3:45

  5. 25:15Agent-first services should let agents handle setup and deployment2:21

  6. 27:40You can outsource thinking but not understanding2:04Up next

Transcript

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

  1. 25:19

    with agents that don't just chat. They have real permissions. They have local context. They actually take action on your behalf. What does the world look like when we all start to live in that world? Yeah, I think a lot of people probably here are excited about what this native agentic environment looks like. And everything has to be rewritten. Everything is still fundamentally written for humans and has to be moved around.

  2. 25:45

    I still use, most of the time when I use different frameworks or libraries or things like that, they still have docs that are fundamentally written for humans. This is my favorite pet peeve. Like, I don't, why are people still telling me what to do? Like, I don't want to do anything. What is the thing I should copy paste to my agent? Like, so it's just, every time I'm told, you know, go to this URL or something like that, it's just like, oh, you know.

  3. 26:09

    So everyone is, I think, excited about how do we decompose the workloads that need to happen into fundamentally sensors over the world, actuators over the world. How do we make it agent-native? Basically, describe it to agents first, and then have a lot of automation around, you know, the, yeah, around data structures that are very legible to the LLMs. So I think, yeah, I'm hoping that there's a lot of agent-first infrastructure out there.

  4. 26:36

    And that for Menugen, famously, when I wrote the, I'm not sure how famously, but when I wrote the blog post about Menugen, a lot of the work, a lot of the trouble was not even writing the code for Menugen, it was deploying it in Vercel, because I had to work with all these different services and I had to string them up and I had to go to their settings and the menus and configure my DNS, and it was just so annoying.

  5. 26:56

    And so that's a good example of I would hope that Menugen, that I could give a prompt to an LLM, build Menugen, and that I didn't have to touch anything and it's deployed in that same way on the internet. I think that would be a good kind of a test for whether or not a lot of our infrastructure is becoming more and more agent native. And then ultimately I would say, yeah, I do think we're going towards a world where there's agent representation for people and for organizations.

  6. 27:24

    and I'll have my agent talk to your agent to figure out some of the details of our meetings. Things like that, so. I do think that that's roughly where things are going,