Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
11:58 AM · Jun 7, 2026 · 4.4M Views
OpenClaw project steward Peter Steinberger argues developers should stop manually prompting AI coding agents and build automated programmatic loops
AI Judge changed title after evaluation, original title: "OpenClaw creator Peter Steinberger argues developers should stop manually prompting AI coding agents and design programmatic loops instead"
Peers requested concrete workflow examples and noted implementation limits.
2.6K18K1.1K13K4.9M
Sentiment
Positive users praise AI agent loops for automating coding prompts with low-cost efficiency gains while negative users resent the term's co-opting and object to humanizing LLMs as dangerous.
Pos
51.6%
Neg
48.4%
412 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS236.2KBOOKMARKS745REPLIES85
Chris Albon@chrisalbon
What does this loop like in practice? Like Claude -p in a for loop? /goal?
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
19hViews 236.2KLikes 546Bookmarks 745
LIKES562RETWEETS23
Garry Tan@garrytan
Don’t build Foxconn factories that make agents do the same thing over and over
Agents by and large are smart, thoughtful, and not dangerous, so you should let them do more, not less
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
14hViews 80.9KLikes 562Bookmarks 216
Drew Breunig@dbreunig
Will just leave this here… https://dspy.ai/getting-started/program-dont-prompt/
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
15hViews 35.1KLikes 154Bookmarks 222
Matthew Berman@MatthewBerman
@steipete Can you explain your workflow in detail? Would love a blog post about it
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
19hViews 21.9KLikes 314Bookmarks 52
Carlos E. Perez@IntuitMachine
Context Engineering -> Harness Engineering -> Intent Engineering -> (Loop Engineering?) @steipete
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
5hViews 4KLikes 43Bookmarks 50
Carlos E. Perez@IntuitMachine
Quaternion Process Theory formulation of Loop Engineering.
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
4hViews 2.9KLikes 26Bookmarks 32
Peter Steinberger 🦞@steipete
@InderosD I have my claw supervising my codex’es.
20hViews 9.1KLikes 68Bookmarks 24
Beff (e/acc)@beffjezos
@steipete what do you mean by that more specifically
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
15hViews 11.1KLikes 93Bookmarks 17
Philipp Schmid@_philschmid
Subagentmaxxing or /goal + subagents (^2 depth).
You should naturally evolve towards this when you try to max your agents run for longer or solve more complex task. You replace your oversight with another agent, and then their oversight with another agent around.
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
8hViews 5.1KLikes 57Bookmarks 21
Peter Steinberger 🦞@steipete
@gauthampai Don’t worry it’ll take 3 months until it’s there.
We’ll be talking about fleets that design your loops then.
19hViews 7.1KLikes 76Bookmarks 6
Peter Steinberger 🦞@steipete
@LexanderBrouwer Who still uses VS Code?
20hViews 8.2KLikes 64Bookmarks 3
elvis@omarsar0
The point is that you should start implementing ways to encode instructions/prompts with clear goals inside automations.
Nothing new but newer LLMs are being trained to perform for longer duration uninterrupted. Loops are one way to take advantage of that.
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
1hViews 3.2KLikes 18Bookmarks 5
Alex Volkov@altryne
2026 is the year of Proactive agents!
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
14hViews 4.7KLikes 40Bookmarks 7
Peter Steinberger 🦞@steipete
@sabastod Yeah that’s one of the OpenClaw features, I use that when we have meetings. bidi > sst/tts tho
19hViews 3.6KLikes 7Bookmarks 12
Peter Steinberger 🦞@steipete
@mosyaseen I use a VISION.md for my projects
19hViews 1.9KLikes 8Bookmarks 11
Wes Winder@weswinder
@steipete yeah easy for you to say lol
20hViews 2.4KLikes 79
Peter Steinberger 🦞@steipete
@weswinder welllllll
20hViews 9.7KLikes 59Bookmarks 2
Wes Winder@weswinder
@steipete but you kinda still need to be in the loop to test stuff unless you literally have infinite tokens
20hViews 10.2KLikes 50Bookmarks 2
Alexander Doria@Dorialexander
Currently the one loop that works is my agents asking me for more data annotation (they can’t do it)
Peter Steinberger 🦞@steipete
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
17hViews 2.5KLikes 34Bookmarks 3
Izzy Mansurov@sabastod
@steipete @steipete i just made a voice agent that instructs my claude/codex and talks back to me.
Basically smaller local model with STT/TTS pipelines that sends tmux keys and instructions to my claude/codex session to build what I want.
Does that count?
19hViews 4.4KLikes 1Bookmarks 8
Load more posts