--- title: Five principles for working with Loops | daily.dev description: An engineer at Linear who helped build Loops, a feature for automating recurring work with the Linear Agent, shares five principles learned from daily use:... canonical: https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Five principles for working with Loops | daily.dev og:description: An engineer at Linear who helped build Loops, a feature for automating recurring work with the Linear Agent, shares five principles learned from daily use:... og:url: https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq og:image: https://api.daily.dev/og/posts/csBo16TXQ.png og:image:alt: Five principles for working with Loops 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. # Five principles for working with Loops **[Linear](https://daily.dev/sources/linear)** · 6 min read · 12 upvotes · 1 comments ## Summary An engineer at Linear who helped build Loops, a feature for automating recurring work with the Linear Agent, shares five principles learned from daily use: look for recurring or neglected tasks to delegate, build loops incrementally rather than in one shot, lean on the context Loops pull from the workspace and connected tools, use the agent itself to iterate and refine loop instructions, and keep loops visible to the team so others can inspect, adjust, or be notified by them. Concrete examples include security teams triaging vulnerability scans and bug bounty reports, a loop cleaning up deprecated code, bug-autofixing and triage loops, a meeting-prep loop, and a customer success on-call notification loop. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How should I approach building an automated workflow with an AI agent so it doesn't produce unreliable or spammy results? Start small in both scope and consequence, then expand responsibilities gradually as results prove reliable. One example involved a code-cleanup loop that began by only identifying candidate issues, then progressed to creating a limited number of issues per run, and only later was trusted to assign work and delegate it to an agent directly, with a human reviewing the final pull request. _Developers refining agent-driven automation can follow similar incremental rollout patterns via daily.dev._ ### Can an AI agent help fix its own automation instructions when the output isn't what I wanted? Yes, an agent can be asked to diagnose why an automated run underperformed and rewrite its own instructions rather than requiring manual prompt tuning. In one case, a meeting-prep automation was too verbose and searched the wrong Slack channel on its first run; asking the agent to revise itself and rerun it produced a much closer result after a couple of minutes of back-and-forth. _Teams iterating on agent workflows can compare approaches to self-correcting automation on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@kartiknvj** · 1 upvotes > Building loops incrementally matches what I've seen with recurring agent jobs: the one-shot version looks fine on day one and quietly drifts by week three. The security loop triaging bug bounty reports is the example I'd love more detail on. Do you keep a human sign-off before a loop closes or reprioritizes an issue, or does it only comment and notify? ## Similar posts on daily.dev - [Introducing Loops](https://daily.dev/posts/introducing-loops-sxhylm1vx) · Linear · 41 upvotes · 1 comments - [Loop Engineering](https://daily.dev/posts/loop-engineering-h663rbtdz) · Elevate · 3 upvotes · 0 comments - [Loop Engineering, Clearly Explained\!](https://daily.dev/posts/loop-engineering-clearly-explained--mt3qmkm25) · Daily Dose of Data Science \| Avi Chawla \| Substack · 3 upvotes · 0 comments - [An Introduction to Loop Engineering](https://daily.dev/posts/an-introduction-to-loop-engineering-7ctzwxfxz) · Machine Learning Mastery · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#automation](https://daily.dev/tags/automation), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq) ```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":"Five principles for working with Loops","url":"https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq"},"datePublished":"2026-10-13T17:58:29.789Z","dateModified":"2026-10-13T18:34:28.270Z","description":"An engineer at Linear who helped build Loops, a feature for automating recurring work with the Linear Agent, shares five principles learned from daily use:...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/34a495e91e9254dbcb6413b8e86d891a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/34a495e91e9254dbcb6413b8e86d891a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Linear","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":"Linear","logo":"https://media.daily.dev/image/upload/s--ntgmTyoI--/f_auto/v1716187332/logos/linear","url":"https://daily.dev/sources/linear"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":12},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"ai-agents,automation,mcp","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Linear","item":"https://daily.dev/sources/linear"},{"@type":"ListItem","position":3,"name":"Five principles for working with Loops"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq","comment":[{"@type":"Comment","text":"Building loops incrementally matches what I’ve seen with recurring agent jobs: the one-shot version looks fine on day one and quietly drifts by week three. The security loop triaging bug bounty reports is the example I’d love more detail on. Do you keep a human sign-off before a loop closes or reprioritizes an issue, or does it only comment and notify?","datePublished":"2026-10-14T16:30:55.975Z","url":"https://daily.dev/posts/csBo16TXQ#c-2SxkihBU2","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"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/five-principles-for-working-with-loops-csbo16txq#faq","mainEntity":[{"@type":"Question","name":"How should I approach building an automated workflow with an AI agent so it doesn't produce unreliable or spammy results?","acceptedAnswer":{"@type":"Answer","text":"Start small in both scope and consequence, then expand responsibilities gradually as results prove reliable. One example involved a code-cleanup loop that began by only identifying candidate issues, then progressed to creating a limited number of issues per run, and only later was trusted to assign work and delegate it to an agent directly, with a human reviewing the final pull request. Developers refining agent-driven automation can follow similar incremental rollout patterns via daily.dev."}},{"@type":"Question","name":"Can an AI agent help fix its own automation instructions when the output isn't what I wanted?","acceptedAnswer":{"@type":"Answer","text":"Yes, an agent can be asked to diagnose why an automated run underperformed and rewrite its own instructions rather than requiring manual prompt tuning. In one case, a meeting-prep automation was too verbose and searched the wrong Slack channel on its first run; asking the agent to revise itself and rerun it produced a much closer result after a couple of minutes of back-and-forth. Teams iterating on agent workflows can compare approaches to self-correcting automation on daily.dev."}}]} ```