--- title: You can just ask AI to do things | daily.dev description: A developer describes handing more and more tasks to AI agents instead of doing them manually. Examples include asking an agent to start the dev server, run... canonical: https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: You can just ask AI to do things | daily.dev og:description: A developer describes handing more and more tasks to AI agents instead of doing them manually. Examples include asking an agent to start the dev server, run... og:url: https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn og:image: https://api.daily.dev/og/posts/Qu5GFVVzn.png og:image:alt: You can just ask AI to do things 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. # You can just ask AI to do things **[sean goedecke](https://daily.dev/sources/seangoedecke)** · 6 min read · 1 upvotes · 1 comments ## Summary A developer describes handing more and more tasks to AI agents instead of doing them manually. Examples include asking an agent to start the dev server, run curl requests against it, and watch metrics and logs during production deploys. The author also asks agents to get a second opinion from other models like GPT-6-Astra and Gemini Argon, and to comb through unread messages each morning via a scheduled 6am job. Design decisions, code review, and writing messages stay manual, and of twenty agent-suggested tasks, often only zero or one gets picked. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What kinds of development tasks can I delegate to an AI coding agent instead of doing them manually? Developers are delegating dev server startup, running curl requests against local servers, watching metrics and logs during production deploys, getting second opinions from other models (such as GPT-6-Astra and Gemini Argon alongside Claude Opus 5.5), triaging unread Slack messages each morning, and even managing and archiving their own agent sessions. _See how other developers are expanding agent delegation for workflows like yours on daily.dev._ ### How can I get a second opinion from multiple AI models on a code change? One approach is to open subagents within a multi-model tool like GitHub Copilot, which has multiple top models built in, and ask it to get feedback from models such as GPT-6-Astra and Gemini Argon on a code change made with a primary model like Claude Opus 5.5. Feedback can then be scanned manually or incorporated automatically depending on how risky the change is. _Developers comparing multi-model agent setups can track approaches like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@nark3d** · 0 upvotes > A 6am unread-message job convinced me, because it turns the agent into a filter over your own backlog and you still decide what to act on. Second opinions from other models are the same move: cheap extra readings you discard most of the time. The discipline is in the zero-or-one-out-of-twenty ratio. I would be more careful about letting the agent set up its own MCP servers and logs, since a tool it configures itself is one you have to audit later. ## Similar posts on daily.dev - [I Spent 1 Month Watching AI Agents Write Code in Production. Here’s What Nobody Tells You.](https://daily.dev/posts/i-spent-1-month-watching-ai-agents-write-code-in-production-here-s-what-nobody-tells-you--ch2azxdgp) · Medium · 3 upvotes · 0 comments - [AI coding agents made me a better programmer, but only after I stopped letting them write the code](https://daily.dev/posts/ai-coding-agents-made-me-a-better-programmer-but-only-after-i-stopped-letting-them-write-the-code-p4t6q31t4) · XDA Developers · 0 upvotes · 0 comments - [AI Agents Are Coming for Every Role](https://daily.dev/posts/ai-agents-are-coming-for-every-role-xvkahnrdz) · Kilo Blog · 3 upvotes · 3 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#github](https://daily.dev/tags/github), [#ai-coding](https://daily.dev/tags/ai-coding), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn) ```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":"You can just ask AI to do things","url":"https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn"},"datePublished":"2026-10-29T08:05:12.710Z","dateModified":"2026-10-29T08:05:36.710Z","description":"A developer describes handing more and more tasks to AI agents instead of doing them manually. Examples include asking an agent to start the dev server, run...","image":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","thumbnailUrl":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","isAccessibleForFree":true,"articleSection":"sean goedecke","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":"sean goedecke","logo":"https://media.daily.dev/image/upload/s--WNgiZyDx--/f_auto,q_auto/v1765713419/logos/seangoedecke","url":"https://daily.dev/sources/seangoedecke"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"ai-agents,github,ai-coding,claude-code","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"sean goedecke","item":"https://daily.dev/sources/seangoedecke"},{"@type":"ListItem","position":3,"name":"You can just ask AI to do things"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn","comment":[{"@type":"Comment","text":"A 6am unread-message job convinced me, because it turns the agent into a filter over your own backlog and you still decide what to act on. Second opinions from other models are the same move: cheap extra readings you discard most of the time. The discipline is in the zero-or-one-out-of-twenty ratio. I would be more careful about letting the agent set up its own MCP servers and logs, since a tool it configures itself is one you have to audit later.","datePublished":"2026-10-30T11:29:26.004Z","url":"https://daily.dev/posts/Qu5GFVVzn#c-TGqTTwzQK","author":{"@type":"Person","name":"Adam","url":"https://daily.dev/nark3d","image":"https://avatars.githubusercontent.com/u/2162621?v=4"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/you-can-just-ask-ai-to-do-things-qu5gfvvzn#faq","mainEntity":[{"@type":"Question","name":"What kinds of development tasks can I delegate to an AI coding agent instead of doing them manually?","acceptedAnswer":{"@type":"Answer","text":"Developers are delegating dev server startup, running curl requests against local servers, watching metrics and logs during production deploys, getting second opinions from other models (such as GPT-6-Astra and Gemini Argon alongside Claude Opus 5.5), triaging unread Slack messages each morning, and even managing and archiving their own agent sessions. See how other developers are expanding agent delegation for workflows like yours on daily.dev."}},{"@type":"Question","name":"How can I get a second opinion from multiple AI models on a code change?","acceptedAnswer":{"@type":"Answer","text":"One approach is to open subagents within a multi-model tool like GitHub Copilot, which has multiple top models built in, and ask it to get feedback from models such as GPT-6-Astra and Gemini Argon on a code change made with a primary model like Claude Opus 5.5. Feedback can then be scanned manually or incorporated automatically depending on how risky the change is. Developers comparing multi-model agent setups can track approaches like this on daily.dev."}}]} ```