Forget Prompt Engineering: 'Loop Engineering' Is All the Rage Now (businessinsider.com)
- Reference: 0184075160
- News link: https://developers.slashdot.org/story/26/06/25/0546238/forget-prompt-engineering-loop-engineering-is-all-the-rage-now
- Source link: https://www.businessinsider.com/what-are-loops-ai-engineering-tips-2026-6
> For the most powerful voices in AI, [1]it's all about being in the loop . Claude Code creator Boris Cherny recently said he doesn't write his own AI prompts much anymore. Thanks to loops, he doesn't have to. "It's an agent that prompts Claude," Cherny recently [2]told CNBC , adding, "I don't write the prompt anymore. Claude writes the prompt, and now I'm talking to that new Claude that is kind of coordinating." In the same interview, Cherny said that loops and a similar feature were examples of the kind of work he would be proudest of in a decade.
>
> Cherny isn't the only one embracing "loop engineering." OpenAI engineer Peter Steinberger, the creator of the viral OpenClaw project, wrote a public reminder to users who are still writing out prompts for AI agents. "Here's your monthly reminder that you shouldn't be prompting coding agents anymore," Steinberger [3]wrote recently on X. "You should be designing loops that prompt your agents." [...] Steinberger shared an example of a loop he uses: "Tell codex to maintain your repos, wake up every 5 minutes and direct work to threads. That makes it easy to parallelize+steer work as needed."
Claire Vo, founder of ChatPRD and host of the "How I AI," said, "it's really just reminding people that you don't have to use your human fingers to type in a prompt in order for your agent to do work on your behalf."
The days of directly prompting generative AI coding tools are "kind of over, or at least some think it's going to be," Addy Osmani, director of Google Cloud, [4]wrote in his post explaining the concept.
[1] https://www.businessinsider.com/what-are-loops-ai-engineering-tips-2026-6
[2] https://x.com/PawelHuryn/status/2069363303952818474
[3] https://x.com/steipete/status/2063697162748260627
[4] https://addyosmani.com/blog/loop-engineering/
Questions (Score:2)
I'm confused about how this works. If I don't give a careful sequence of prompts to lead AI then it can go off the rails. For example, it forgets parts of the code after awhile and has to be reminded to reuse a function instead of rewriting it. What is better about the watcher agent that it will keep the AI on track? Also, when will there be a watcher agent watcher? That's what I really want
Re: (Score:1)
If you run into situations where the AI is fundamentally doing something wrong, like not reusing code, or not writing secure code, etc. then that is a flaw in your setup. The skill.md files you gave it, the overarching agents.md file, or possibly the MCP setup. With the right setup though, there is no need to continue to prompt per task. The AI has reached a point where it can (assuming you can afford it) plan/work/test/fix until the goals are reached - at least on the frontier models.
Ok. (Score:2)
So you're telling Claude something vague and washy, then Claude invents a prompt that might vaguely possibly be somehow related to what you want along with a drink that is almost but not entirely quite unlike tea. Claude then recurses through this until it has a Celtic knot so intricate that it has its own Hausdorff dimension. What burps out is a product that is completely useless and patented to the Sirius Cybernetics Corporation.
loops (Score:2)
Just point a bunch of AI agents at each other, don't prompt them, and magic happens. Don't talk to your agents you knuckle dragger. OMG y wud u typ?
Yo Boss, check my lines of code.
Uhg (Score:2)
"It's an agent that prompts Claude,"
It's AI all the way down
So it begins (Score:2)
So, because blackbox AI wasn't sloppy and incompetent enough, we now have AI middle managers.
Remember Murphy's law of delegation: "Teamwork is essential; it allows you to blame someone else when things go wrong."
To quote the Bobs (Score:3, Insightful)
So what exactly would you say you *do* here?