--- title: Your coding agent got the onboarding your developers... description: Organizations are pouring effort into onboarding documents, small-batch workflows, and reliable test suites for AI coding agents—practices developers had been... canonical: https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Your coding agent got the onboarding your developers never did | daily.dev og:description: Organizations are pouring effort into onboarding documents, small-batch workflows, and reliable test suites for AI coding agents—practices developers had been... og:url: https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe og:image: https://api.daily.dev/og/posts/z8H70SIpE.png og:image:alt: Your coding agent got the onboarding your developers never did 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. # Your coding agent got the onboarding your developers never did **[The New Stack](https://daily.dev/sources/newstack)** · 5 min read · 3 upvotes · 2 comments ## Summary Organizations are pouring effort into onboarding documents, small-batch workflows, and reliable test suites for AI coding agents—practices developers had been requesting for years without success. Steve Yegge's essay 'The Shape of Things to Come' claims coding agents deserve welfare consideration, but the piece pivots to a sharper observation: teams keep AGENTS.md files lean and current because tokens cost money, while human onboarding docs rot indefinitely. Google's 2025 DORA report shows 90% AI adoption but uneven benefits tied to deployment pipeline quality, and Faros AI telemetry shows context-switching has worsened sharply for developers working alongside agents. The piece argues that the discipline now applied for agents—small batches, fast feedback, clean tests—was dismissed as impractical when it was only for people. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is an AGENTS.md file used for in AI coding agent setups? AGENTS.md is a plain-text or markdown file that gives coding agents onboarding context, including tech stack details, build and test commands, off-limits directories, and team conventions. Best practice keeps it under roughly 300 lines, since every line gets re-read each session; HumanLayer's team keeps theirs under 60 lines for efficiency. _Teams refining how they brief coding agents can compare notes on setup practices through daily.dev._ ### What did Google's 2025 State of AI-assisted Software Development report find about AI adoption in software teams? Adoption reached 90% of organizations, a 14-point jump in a single year, but benefits were uneven across teams. The report found AI amplifies existing software delivery capability: strong engineering systems get stronger while dysfunctional ones become more chaotic, with deployment pipeline quality determining which outcome a team gets. _Engineering leaders weighing AI rollout strategy can track findings like these on daily.dev._ ### How has AI assistance affected developer context switching according to Faros AI telemetry? Developers using AI assistance in 2026 were juggling 67.4% more pull-request contexts and 17.7% more task contexts per day than before, up sharply from 47% and 9% the prior year. Work restarts rose almost 14%, and more than a quarter of in-progress tasks sat untouched for a week or longer, pointing to context-switching strain on both humans and agents. _Developers wrestling with AI-driven context switching can follow related productivity research on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@kartiknvj** · 0 upvotes > The onboarding framing is sharp, an agent with the repo's full context outpaces a new hire mostly because nobody wrote the human that much documentation. The catch I keep hitting is that the same context makes the agent confidently wrong when the docs are stale. Curious how the piece handles context that has drifted from the actual code. ## Similar posts on daily.dev - [Simon Willison’s Weblog](https://daily.dev/posts/simon-willison-s-weblog-ypcurxob3) · Hacker News · 1 upvotes · 1 comments - [Get out of your developer bubble to survive the AI bubble](https://daily.dev/posts/get-out-of-your-developer-bubble-to-survive-the-ai-bubble-yj8wtvnig) · Stack Overflow Blog · 0 upvotes · 0 comments - [What Nobody's Telling You About AI Agents and Team Development](https://daily.dev/posts/what-nobody-s-telling-you-about-ai-agents-and-team-development-vwl3pashl) · RUBYLAND · 0 upvotes · 0 comments - [Coding for agents](https://daily.dev/posts/coding-for-agents-gzqxu77mk) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#company-culture](https://daily.dev/tags/company-culture), [#dora-metrics](https://daily.dev/tags/dora-metrics) [View this post on daily.dev](https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe) ```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":"Your coding agent got the onboarding your developers never did","url":"https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe"},"datePublished":"2026-08-19T17:09:49.837Z","dateModified":"2026-09-14T07:55:19.534Z","description":"Organizations are pouring effort into onboarding documents, small-batch workflows, and reliable test suites for AI coding agents—practices developers had been...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4c924ee49bd0e1ab38f7548414371977?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4c924ee49bd0e1ab38f7548414371977?_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":2,"discussionUrl":"https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"keywords":"ai-agents,company-culture,dora-metrics","timeRequired":"PT5M"} {"@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":"Your coding agent got the onboarding your developers never did"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe","comment":[{"@type":"Comment","text":"The onboarding framing is sharp, an agent with the repo’s full context outpaces a new hire mostly because nobody wrote the human that much documentation. The catch I keep hitting is that the same context makes the agent confidently wrong when the docs are stale. Curious how the piece handles context that has drifted from the actual code.","datePublished":"2026-08-19T18:59:58.427Z","url":"https://daily.dev/posts/z8H70SIpE#c-fQwfXFeAT","author":{"@type":"Person","name":"kartik-nvjk","url":"https://daily.dev/kartiknvj","image":"https://media.daily.dev/image/upload/s--3gGgsVCw--/f_auto/v1781456774/avatars/avatar_TvTVeiMdkRCqWUDullFmy?_a=BAMAMiWQ0"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe#faq","mainEntity":[{"@type":"Question","name":"What is an AGENTS.md file used for in AI coding agent setups?","acceptedAnswer":{"@type":"Answer","text":"AGENTS.md is a plain-text or markdown file that gives coding agents onboarding context, including tech stack details, build and test commands, off-limits directories, and team conventions. Best practice keeps it under roughly 300 lines, since every line gets re-read each session; HumanLayer's team keeps theirs under 60 lines for efficiency. Teams refining how they brief coding agents can compare notes on setup practices through daily.dev."}},{"@type":"Question","name":"What did Google's 2025 State of AI-assisted Software Development report find about AI adoption in software teams?","acceptedAnswer":{"@type":"Answer","text":"Adoption reached 90% of organizations, a 14-point jump in a single year, but benefits were uneven across teams. The report found AI amplifies existing software delivery capability: strong engineering systems get stronger while dysfunctional ones become more chaotic, with deployment pipeline quality determining which outcome a team gets. Engineering leaders weighing AI rollout strategy can track findings like these on daily.dev."}},{"@type":"Question","name":"How has AI assistance affected developer context switching according to Faros AI telemetry?","acceptedAnswer":{"@type":"Answer","text":"Developers using AI assistance in 2026 were juggling 67.4% more pull-request contexts and 17.7% more task contexts per day than before, up sharply from 47% and 9% the prior year. Work restarts rose almost 14%, and more than a quarter of in-progress tasks sat untouched for a week or longer, pointing to context-switching strain on both humans and agents. Developers wrestling with AI-driven context switching can follow related productivity research on daily.dev."}}]} ```