Thread Truncated (Cap Enforced)
Only the first 20 tweets are unrolled into slides to ensure reliable PDF exporting and high server performance.
Canvas & Ratio
Choose your destination platform format
Layout Template
Choose a content structure for your slides
Preset Themes
Typography & Sizing
Brand Kit Customization
AGENCYConfigure brand assets for headers & footers
Outro Slide CTA
Customize your closing call-to-action slide
Background Pattern
Build Your Carousel
Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!
A few weeks ago @addyosmani, formerly of Google Chrome, now author of Beyond Vibe Coding, published a piece called Loop Engineering. It opened with a quote from @steipete: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents." Boris Cherny, head of Claude Code at Anthropic, said the same thing: "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."
LangChain followed with The Art of Loop Engineering, laying out a four-level architecture. Tooling appeared: LoopFlow on GitHub, Neuralyzer for self-wiping agent context windows. The term now has 987 results on the Hacker News search API.
It is also a good description of a distributed system. We have been building those for twenty years.
## What Loop Engineering Actually Describes
Per Addy Osmani and LangChain's own writing, a production loop has four levels:
<b>The agent loop:</b> a model calling tools repeatedly until a task completes.
<b>A verification loop:</b> a grader checks output against a rubric and retries on failure.
<b>An event-driven loop:</b> cron schedules or webhooks trigger agent runs automatically.
<b>A hill-climbing loop: </b>production traces feed an analysis agent that rewrites the harness configuration.
Surrounding everything: memory "a markdown file, or a Linear board, anything that lives outside the single conversation and holds what's done and what is next." Addy's words, not mine.
This is a complete description of an event-driven, observable, stateful distributed system with retry logic, dead-letter handling, pub/sub fan-out, and durable external state.
## Let me translate the terminology:
The naming is different. The systems are the same.
A developer on Hacker News built a loop engineering pipeline for Korean-to-English translation before the term existed — <b>a plan → execute → critique → repair loop</b> with a separate reference translator as an "impartial witness," a translation memory to prevent terminology drift, and an output writer appending incrementally to disk. Textbook loop engineering architecture.
Their conclusion: "the critic kept flagging that the translation is not good enough and looping back and the translator was not able to translate good enough for the critic to be satisfied... after a couple of weeks I kind of gave up."
An unobservable retry loop with no circuit breaker, no dead-letter queue, no backpressure, and no durable state is loop engineering on paper. In production it just runs until something breaks.
## iii's Harness Worker
