<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg" -->

---
title: Agents write code. They don’t do software engineering.
description: Long-running coding agents can now submit pull requests autonomously, but the real question isn&#x27;t how much to supervise them — it&#x27;s which categories of work...
canonical: https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Agents write code. They don’t do software engineering. | daily.dev
og:description: Long-running coding agents can now submit pull requests autonomously, but the real question isn&#x27;t how much to supervise them — it&#x27;s which categories of work...
og:url: https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg
og:image: https://api.daily.dev/og/posts/39qO8ONeG.png
og:image:alt: Agents write code. They don’t do software engineering.
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents write code. They don’t do software engineering.

**[The New Stack](https://daily.dev/sources/newstack)** · 8 min read · 3 upvotes · 0 comments

## Summary

Long-running coding agents can now submit pull requests autonomously, but the real question isn't how much to supervise them — it's which categories of work they should own. Writing code is pattern recognition that LLMs excel at, while software engineering involves trade-offs, business context, and judgment that agents lack. A three-tier framework is proposed: Tier 1 (agent-led, developer-reviewed) for boilerplate and scaffolding; Tier 2 (agent-assisted, developer-guided) for feature work within known domains; and Tier 3 (developer-led, agent-supported) for architectural decisions and cross-boundary changes. Over-allocating to agents causes costly rework; under-allocating wastes developer time on mechanical tasks. Teams that audit their work distribution — not just their agents — reclaim developer time for high-judgment work that agents cannot yet handle.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://thenewstack.io/ai-agents-software-engineering/>

## Similar posts on daily.dev

- [The Factory Model: How Coding Agents Changed Software Engineering](https://daily.dev/posts/the-factory-model-how-coding-agents-changed-software-engineering-eavrwedl9) · Addy Osmani · 64 upvotes · 2 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#productivity](https://daily.dev/tags/productivity), [#ai-agents](https://daily.dev/tags/ai-agents), [#distributed-systems](https://daily.dev/tags/distributed-systems)

[View this post on daily.dev](https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Agents write code. They don’t do software engineering.","url":"https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg"},"datePublished":"2026-03-16T12:09:17.979Z","dateModified":"2026-03-16T12:09:42.480Z","description":"Long-running coding agents can now submit pull requests autonomously, but the real question isn't how much to supervise them — it's which categories of work...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c8ef27516bbd822f703c79831d4b2f15?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c8ef27516bbd822f703c79831d4b2f15?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/agents-write-code-they-don-t-do-software-engineering--39qo8oneg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,productivity,ai-agents,distributed-systems","timeRequired":"PT8M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Agents write code. They don’t do software engineering."}]}
```

