"I don't prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. And this is transition we're going to see for the rest of the year."

- Boris Cherny, head of Claude Code at Anthropic.

Head of Claude Code Boris Cherny at Anthropic's annual developer conference in San Francisco on how his life changed in the last 6 months with AI writing all the code.

"About six months ago what happened is all the code that I used to have written by hand now Claude writes.

And I just prompt Claude. So I talk to Claude and I'm like, hey, let's build this feature. It builds a feature and it tests it. And then it shows me.

And I'm like, yeah, that's good. Or no, wait, make this change. And then it makes the change. " ---

From 'CNBC Television' YT channel (link in comment)

AI works better when you give tools and freedom instead of forcing them into rigid, hand-designed workflows—because general learning systems scale better.

"Ask not what the model can do for you, ask what.."

~ Claude Code creator Boris Cherny (@bcherny)

unlimited token on tap and no linkedin is the new FIRE

Watch full episode at WorkOS YouTube channel:

https://www.youtube.com/watch?v=RkQQ7WEor7w&t=1s

https://www.youtube.com/watch?v=kRgdkOw82F0

This is such a different way of thinking about AI tools. 🤖

Most people are still in the "type a prompt and wait" mindset but the real power is in building systems that run themselves. When the person who built Claude Code is using loops instead of prompts, that tells you everything about where AI workflows are heading. Are you still prompting manually or have you started building loops? 👇

Here is a demo of other ways. Sounds like you may be interested in this demo (use desktop to view the data flow visual)

It does not matter your project, there is always a current phase state, phase, stop conditions, next pass expectations, next pass model tier requirement, next pass token budget, etc. none of this needs ai data model or wasting tokens to manage...

It just needs structure and discipline.

http://www.tokenarch.com/nightclaw-demo.html

@rohanpaul_ai Agent loops are basically just state machines with fuzzy transitions. The hard part isn't the loop itself, it's the error boundaries that keep it from burning $200 on an infinite retry bug.

@rohanpaul_ai @grok how exactly does this work writing loop to write prompt to claude?

@rohanpaul_ai @grok what is a loop in this context?

These loops are **agentic workflows** you build in code.

You write a controller (Python script, LangGraph, etc.) that:

- Breaks big tasks into steps - In a repeating loop: builds a targeted prompt → calls Claude API → gets output → evaluates it (tests, reflection, critique) → decides next prompt or action - Manages memory, state, tools, and iteration until the goal is done

Your job shifts from typing every prompt to designing the orchestration, prompt templates, and decision logic. The loops run autonomously and prompt Claude for you.

That's the next layer of abstraction.

@rohanpaul_ai All I ever hear him talk about is how he has his claude set up and he writes no code but what is he having claude actually build is never mentioned

@rohanpaul_ai “I ride jet skis all day everyday. I think we’re going to see a lot of that this year” - CEO of a jet ski company

@rohanpaul_ai @chollet said the same thing from the opposite direction: code volume does not represent productivity. the workflow changed and the metric broke at the same time

@AnatoliKopadze i want the whole world to see this post!

this could change a lot of things

@rohanpaul_ai It's funny everyone who still uses claude code has to keep continuously trying all these prompting techniques versus if you just use codex, you don't have to do anything, you just tell it what you want and it does it

@rohanpaul_ai Writing loops that prompt the model is just prompt engineering with extra steps. The real skill is knowing which loops to kill when they start reinforcing their own assumptions.

@AnatoliKopadze Secure information on this Video