<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/sGB4AHNCg" -->

---
title: Maintaining quality while agents write the code | daily.dev
description: Engineering managers are urged to rethink code review and team practices now that AI coding agents let engineers produce many PRs quickly. The piece argues...
canonical: https://daily.dev/posts/sgb4ahncg
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Maintaining quality while agents write the code | daily.dev
og:description: Engineering managers are urged to rethink code review and team practices now that AI coding agents let engineers produce many PRs quickly. The piece argues...
og:url: https://daily.dev/posts/sgb4ahncg
og:image: https://api.daily.dev/og/posts/sGB4AHNCg.png
og:image:alt: Post cover image
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.

# Maintaining quality while agents write the code

**[Stephane Moreau](https://daily.dev/sources/ld3qs65tsjruwey40hj4p)** · [@stmoreau](https://daily.dev/stmoreau) · 16 upvotes · 2 comments

## Summary

Engineering managers are urged to rethink code review and team practices now that AI coding agents let engineers produce many PRs quickly. The piece argues that thinking about design decisions - not just writing code - is the part of engineering that must not disappear, citing OpenCode's co-founder Dax on shifting from 95% thinking/5% coding to near total focus on thinking. It recommends slowing down for high-impact changes (new data models, interfaces, operational behavior changes) with lightweight ADRs, ensuring a human owner can explain what changed and why, and tracking review capacity as a real constraint rather than praising raw PR throughput. It references an Anthropic study suggesting engineers using AI while learning a new library scored lower on follow-up quizzes, and suggests three questions to ask PR authors to surface whether they understand irreversible decisions, assumptions, and risky areas of their own agent-assisted code.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.blog4ems.com/p/maintaining-quality-agentic-engineering>

## Community discussion

Top comments from developers on daily.dev.

**@tekn0wledg** · 2 upvotes

> The real challenge is domain knowledge. It's easy to just automate your PRs cuz they are tedious.... it's another thing to know and understand the impact of those PRs against the architecture, scalability and usability of the apps you are building.
>
> Literally saw Claude approve a PR today that had like 19 new tables added to a schema (for a database that already had 100+ tables) and it passed clean, because it followed the rules of the repo.... but it was NOT the correct design decision.
>
> So now I get tagged on all PRs that will have updates to certain portions of our architecture. Everything...

## Similar posts on daily.dev

- [Agentic Code Review](https://daily.dev/posts/agentic-code-review-0ue8fcsa1) · Addy Osmani · 146 upvotes · 14 comments
- [Agile in the Age of AI](https://daily.dev/posts/agile-in-the-age-of-ai-88uovbs2o) · Tech Lead Digest · 2 upvotes · 0 comments
- [Code review is burning out your best engineers](https://daily.dev/posts/code-review-is-burning-out-your-best-engineers-5anqvkfac) · The New Stack · 0 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#architecture](https://daily.dev/tags/architecture), [#leadership](https://daily.dev/tags/leadership), [#code-review](https://daily.dev/tags/code-review), [#technical-debt](https://daily.dev/tags/technical-debt)

[View this post on daily.dev](https://daily.dev/posts/sgb4ahncg)

```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":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/sgb4ahncg","headline":"Maintaining quality while agents write the code","text":"Shared: Maintaining quality while agents write the code","url":"https://daily.dev/posts/sgb4ahncg","datePublished":"2026-09-29T11:31:44.207Z","dateModified":"2026-09-29T11:32:55.141Z","author":{"@type":"Person","name":"Stephane Moreau","url":"https://daily.dev/stmoreau","image":"https://lh3.googleusercontent.com/a/ACg8ocJe5l4RcMM86d5Sjq5jiAnM75yewxpRhegwj5IkYtlCbegq=s96-c","description":"Senior Engineering Manager | Join 10,000+ Leaders in my Blog for Engineering Managers","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":2680}},"image":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":16},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/KeIjFG54v"},"comment":[{"@type":"Comment","text":"The real challenge is domain knowledge. It’s easy to just automate your PRs cuz they are tedious… it’s another thing to know and understand the impact of those PRs against the architecture, scalability and usability of the apps you are building.\nLiterally saw Claude approve a PR today that had like 19 new tables added to a schema (for a database that already had 100+ tables) and it passed clean, because it followed the rules of the repo… but it was NOT the correct design decision.\nSo now I get tagged on all PRs that will have updates to certain portions of our architecture. Everything low-risk goes through automated. Everything else #humanintheloop","datePublished":"2026-10-01T19:19:31.986Z","url":"https://daily.dev/posts/sGB4AHNCg#c-VCe8xkfMB","author":{"@type":"Person","name":"Scott Davis","url":"https://daily.dev/tekn0wledg","image":"https://avatars.githubusercontent.com/u/355212?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/sources/ld3qs65tsjruwey40hj4p","name":"Stephane Moreau"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Stephane Moreau","item":"https://daily.dev/sources/ld3qs65tsjruwey40hj4p"},{"@type":"ListItem","position":3,"name":"Maintaining quality while agents write the code"}]}
```

