# Linear

Linear is a work-tracking application for teams that plan, track, and ship product work, with issue tracking and GitHub pull-request automation.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How the groundcover team works now: Slack for people, Linear for agents

DevFeed: [How the groundcover team works now: Slack for people, Linear for agents](<https://devfeed.tech/articles/how-the-groundcover-team-works-now-slack-for-people-linear-for-agents-134508.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/slack-for-people-linear-for-agents>)

Author: Anais Dotis

Published: 2026-11-15T10:03:00Z

Content type: article

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-code-review](<https://devfeed.tech/tags/ai-code-review.md>), [apis](<https://devfeed.tech/tags/apis.md>), [audits](<https://devfeed.tech/tags/audits.md>), [automated-remediation](<https://devfeed.tech/tags/automated-remediation.md>), [autonomous-infrastructure](<https://devfeed.tech/tags/autonomous-infrastructure.md>), [ci-cd-pipelines](<https://devfeed.tech/tags/ci-cd-pipelines.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [groundcover](<https://devfeed.tech/tags/groundcover.md>), [investigations](<https://devfeed.tech/tags/investigations.md>), [linear](<https://devfeed.tech/tags/linear.md>), [root-cause-analysis](<https://devfeed.tech/tags/root-cause-analysis.md>), [slack](<https://devfeed.tech/tags/slack.md>)

### AI overview

The team uses agents to handle lookup, ticket upkeep, and first-pass code review so engineers can focus on design and judgment. Engineers discuss work in Slack; agents create and update Linear tickets from specs and answer questions by checking documentation. Most changes now go directly to pull requests, where reviewers assess both implementation and approach; line-by-line review remains for high-risk areas such as scale, data correctness, and customer-facing APIs. The team bounds retries, checks invariants before saving, keeps interfaces simple, maintains design documents, and rejects code likely to create technical debt. Agents can produce tests but do not yet choose what new information a feature should measure or how to present it. For remediation, groundcover proposes human-reviewed fixes first; teams may later opt into automation. Its existing infrastructure tool allows cluster-by-cluster adoption, logs changes, and can restore prior values. The planned CI/CD integration would compare pre-deploy signals with post-deploy data to flag regressions.

### Source excerpt

Building groundcover Investigations changed more than our product and how you can use groundcover to perform root cause analysis and roll out fixes. It also changed how the team building groundcover Investigations works day to day. Agents now handle much of the lookup work, the ticket updates and the first pass of code review. The engineers spend more of their time making decisions.

## Introducing Mobile Diffs

DevFeed: [Introducing Mobile Diffs](<https://devfeed.tech/articles/introducing-mobile-diffs-121226.md>)

Original publisher: [Read original article](<https://linear.app/now/mobile-diffs>)

Published: 2026-11-05T16:44:00Z

Content type: release

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Android](<https://devfeed.tech/topics/android.md>), [iOS](<https://devfeed.tech/topics/ios.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [android](<https://devfeed.tech/tags/android.md>), [app](<https://devfeed.tech/tags/app.md>), [changes](<https://devfeed.tech/tags/changes.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [comment](<https://devfeed.tech/tags/comment.md>), [diffs](<https://devfeed.tech/tags/diffs.md>), [ios](<https://devfeed.tech/tags/ios.md>), [linear](<https://devfeed.tech/tags/linear.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [phone](<https://devfeed.tech/tags/phone.md>), [review](<https://devfeed.tech/tags/review.md>), [send](<https://devfeed.tech/tags/send.md>), [threads](<https://devfeed.tech/tags/threads.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Linear Diffs is available on iOS and Android, letting users review pull requests and continue review work from a phone. Guided Reviews divide a PR into sections that explain what changed and why; users can comment, reply to teammates' or agents' review threads, and send fixes back to an agent. Review requests, approvals, and comments appear in the home screen and Linear Inbox, preview links open on the device, and files marked viewed sync between phone and desktop. To use it, install the latest Linear app; workspaces not yet using Diffs need an admin to upgrade the GitHub integration for code access.

### Source excerpt

Diffs, Linear's fast and focused code review, is now on iOS and Android. Approve changes, reply to threads, and send work back to agents from your phone.

## How a beagle-shaped AI agent ships code to madewithvuejs.com

DevFeed: [How a beagle-shaped AI agent ships code to madewithvuejs.com](<https://devfeed.tech/articles/how-a-beagle-shaped-ai-agent-ships-code-to-madewithvuejs-com-102791.md>)

Original publisher: [Read original article](<https://blog.sentry.io/beagle-ai-agent-workflows/>)

Author: Armin Ulrich

Published: 2026-10-27T09:00:00Z

Content type: article

Language: en

Sources: [Sentry](<https://devfeed.tech/sources/sentry-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Continuous Deployment (CD)](<https://devfeed.tech/topics/continuous-deployment.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [bugfixes](<https://devfeed.tech/topics/bugfixes.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [all](<https://devfeed.tech/tags/all.md>), [allowed](<https://devfeed.tech/tags/allowed.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [code](<https://devfeed.tech/tags/code.md>), [content](<https://devfeed.tech/tags/content.md>), [features](<https://devfeed.tech/tags/features.md>), [github](<https://devfeed.tech/tags/github.md>), [linear](<https://devfeed.tech/tags/linear.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [production](<https://devfeed.tech/tags/production.md>), [sentry](<https://devfeed.tech/tags/sentry.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

Milly, a cloud-hosted agent running in a custom harness, scouts Vue.js projects and can build and ship assigned features or fix production bugs. It uses GitHub to commit, merge, and deploy code; Linear to receive tickets and link related commits; Sentry's MCP to inspect production issues and resolve them after fixes, with Seer available for complex debugging; and Discord to report content finds. In one form update, it fixed an HTML rendering bug and a validation/database length mismatch that had caused eight lost submissions. Its process includes reproducing bugs, writing a failing test before the fix, running the full suite, and checking the live site. It must ask for clarification when briefs are unclear, cannot change production data, credentials, or server configuration, and cannot close Linear tickets. The authors say its autonomy suits their small, content-focused site, where backups and limited user data constrain the potential impact.

### Source excerpt

Meet Milly, the AI agent at madewithvuejs.com that scouts content, ships features, and fixes production bugs using GitHub, Linear, and the Sentry MCP.

## LHB Linux Digest #26.16: Bash Arrays, mapfile, Self-hosted Linear Alternative and More

DevFeed: [LHB Linux Digest #26.16: Bash Arrays, mapfile, Self-hosted Linear Alternative and More](<https://devfeed.tech/articles/lhb-linux-digest-26-16-bash-arrays-mapfile-self-hosted-linear-alternative-and-more-97843.md>)

Original publisher: [Read original article](<https://linuxhandbook.com/newsletter/26-16/>)

Author: Abhishek Prakash

Published: 2026-10-23T12:39:19Z

Content type: tutorial

Language: en

Sources: [Linux Handbook](<https://devfeed.tech/sources/linux-handbook.md>)

Topics: [Bash](<https://devfeed.tech/topics/bash.md>), [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Tutorial](<https://devfeed.tech/topics/tutorial.md>)

Tags: [1-4](<https://devfeed.tech/tags/1-4.md>), [2](<https://devfeed.tech/tags/2.md>), [22](<https://devfeed.tech/tags/22.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [added](<https://devfeed.tech/tags/added.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arrays](<https://devfeed.tech/tags/arrays.md>), [bash](<https://devfeed.tech/tags/bash.md>), [linear](<https://devfeed.tech/tags/linear.md>), [linux](<https://devfeed.tech/tags/linux.md>), [newsletter](<https://devfeed.tech/tags/newsletter.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [values](<https://devfeed.tech/tags/values.md>), [variable](<https://devfeed.tech/tags/variable.md>)

### AI overview

The Bash section explains indexed and associative arrays, including zero-based indexing, element counts, appending, slices, and how quoted "${array[@]}" preserves items containing spaces while "${array[*]}" joins them into one string. It shows mapfile -t with process substitution to load find results into an array. The excerpt also describes itsaplan as a self-hosted, Linear-style project management platform for teams working alongside AI agents, and lazyenv as a terminal interface for managing .env files. It warns that a breach affecting about 1.4% of OpenCode Console users may have exposed third-party API keys, and reports that GitHub Enterprise Cloud can enforce open-source license compliance during pull requests. The certification discount and sale deadline are time-sensitive claims in the newsletter.

### Source excerpt

One variable, many values.

## Dark mode was never on our roadmap. Here's how it got built.

DevFeed: [Dark mode was never on our roadmap. Here's how it got built.](<https://devfeed.tech/articles/dark-mode-was-never-on-our-roadmap-here-s-how-it-got-built-97363.md>)

Original publisher: [Read original article](<https://medium.engineering/dark-mode-was-never-on-our-roadmap-heres-how-it-got-built-b8e0a54c1d12?source=rss----2817475205d3---4>)

Author: Christine Leverett

Published: 2026-10-22T14:01:07Z

Content type: article

Language: en

Sources: [Medium](<https://devfeed.tech/sources/medium.md>)

Topics: [Dark Mode](<https://devfeed.tech/topics/dark-mode.md>), [CSS](<https://devfeed.tech/topics/css.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cache](<https://devfeed.tech/tags/cache.md>), [colors](<https://devfeed.tech/tags/colors.md>), [css](<https://devfeed.tech/tags/css.md>), [dark-mode](<https://devfeed.tech/tags/dark-mode.md>), [dark-theme](<https://devfeed.tech/tags/dark-theme.md>), [design](<https://devfeed.tech/tags/design.md>), [it](<https://devfeed.tech/tags/it.md>), [medium](<https://devfeed.tech/tags/medium.md>), [plan](<https://devfeed.tech/tags/plan.md>), [product](<https://devfeed.tech/tags/product.md>), [programming](<https://devfeed.tech/tags/programming.md>), [project](<https://devfeed.tech/tags/project.md>), [roadmap](<https://devfeed.tech/tags/roadmap.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [team](<https://devfeed.tech/tags/team.md>), [technical](<https://devfeed.tech/tags/technical.md>), [technology](<https://devfeed.tech/tags/technology.md>), [the-web](<https://devfeed.tech/tags/the-web.md>)

### AI overview

Medium shipped dark mode to all readers in under five months, with most of the work done by one engineer between other projects. The approach kept the effort safe, small, and concrete: a staff-only feature flag isolated the work behind the edge cache; CSS `light-dark()` and `color-scheme` let the browser choose the theme before first paint; and small pull requests and AI-assisted audits turned legacy color cleanup into reviewable tasks. The older M2 service required converting styles page by page, preserving existing light colors as fallbacks, and quarantining pages for staff QA before rollout. Design input and manual QA remained necessary: Claude missed issues, including cases where translucent colors depended on what lay beneath them. The reader experience launched to 100% of readers on October 1; M2 pages were still in QA at the time of writing.

### Source excerpt

Keep it safe, keep it small, keep it concrete: How a "someday project" finally shippedImage created by the Medium Brand team Medium has been around for 14 years. In that time, dark mode went from a novelty to a must-have, especially for sites built for reading. In my seven years on the web team, however, it never made it onto our roadmap. Why? Readers asked for it and teammates often asked what it would take, but there was just always another project that needed our engineers more. This year, that finally changed, and I'm so excited to say that (most of) Medium now supports a dark theme! The energy inside the company has been huge, but the cherry on top was hearing from readers who went out of their way to fill out our feedback form just to say thank you. Seriously, who does that? To everyone who wrote in: thank you so much. It feels wonderful to finally deliver this to our readers, and soon to our writers too. This story is about how it happened. Part of it is technical, like why dark mode was harder for us than flipping a few colors. But a big part of it is personal, because the hardest piece for me wasn't the cache or the CSS, but taking the first steps. Starting without a ticket For most of my career, work has reached me as a ticket someone else wrote. I'm good at that. I'm careful, I follow through, and I like finishing things. Dark mode lived in a gap I think a lot of teams have: work the company clearly valued, but kept getting edged out by larger initiatives. It was the first time, though, that I felt strongly enough about something in that gap to try closing it myself. We're a small team, and our design team is even smaller and juggling a ton. But when the web team met to pick a few projects outside our feature work earlier this year, I suggested we finally build it. I believed it could be done without dropping any product work. All we needed was a plan and someone to take the first steps. I didn't want to ask the team to trade something important away, and

## Introducing Tolaria for mobile! 📱

DevFeed: [Introducing Tolaria for mobile! 📱](<https://devfeed.tech/articles/introducing-tolaria-for-mobile-92840.md>)

Original publisher: [Read original article](<https://refactoring.fm/p/introducing-tolaria-mobile>)

Author: Luca Rossi

Published: 2026-10-21T13:13:23Z

Content type: release

Language: en

Sources: [Refactoring](<https://devfeed.tech/sources/refactoring.md>)

Topics: [Mobile](<https://devfeed.tech/topics/mobile.md>), [iOS](<https://devfeed.tech/topics/ios.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [ai-on-mobile](<https://devfeed.tech/topics/ai-on-mobile.md>), [Android](<https://devfeed.tech/topics/android.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [mobile-app-performance](<https://devfeed.tech/topics/mobile-app-performance.md>)

Tags: [1password](<https://devfeed.tech/tags/1password.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [app](<https://devfeed.tech/tags/app.md>), [apps](<https://devfeed.tech/tags/apps.md>), [better](<https://devfeed.tech/tags/better.md>), [bots](<https://devfeed.tech/tags/bots.md>), [bugged](<https://devfeed.tech/tags/bugged.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [build](<https://devfeed.tech/tags/build.md>), [builds](<https://devfeed.tech/tags/builds.md>), [can](<https://devfeed.tech/tags/can.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [coding](<https://devfeed.tech/tags/coding.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [monthly](<https://devfeed.tech/tags/monthly.md>), [updates](<https://devfeed.tech/tags/updates.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Tolaria's iOS app is available on TestFlight for iPhone and iPad, with a visual Markdown editor, Git push and pull with auto-commit, iCloud or Files sync, a command palette, and 19 languages. The release is rough: Git sync is limited to GitHub-cloned repositories, large vaults can be slow to clone, crashes occur, and AI is not yet available. Android is planned but awaits more testing. The author chose React Native chiefly for over-the-air updates, which can deliver fixes without waiting for app reviews. Development now runs mainly on separate Hetzner Linux machines for Codex and Claude Code, with a Mac mini retained for iOS work. Moving CI from GitHub Actions to CircleCI cut the main pipeline from about 15-16 minutes to around four. Verity reviews Claude Code changes using AI review, static analysis, formal proofs, and a knowledge base of decisions. Future plans include an open-source, self-hostable web version with an optional managed service, and deeper integrations with agent hosts; those agent features remain exploratory.

### Source excerpt

Plus a new round of monthly updates on my coding workflow.

## Giving engineers direct ownership of projects

DevFeed: [Giving engineers direct ownership of projects](<https://devfeed.tech/articles/put-a-name-on-it-90125.md>)

Original publisher: [Read original article](<https://www.theengineeringmanager.com/growth/put-a-name-on-it/>)

Author: James Stanier

Published: 2026-10-19T14:51:31Z

Content type: opinion

Language: en

Sources: [The Engineering Manager](<https://devfeed.tech/sources/the-engineering-manager-2.md>)

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [communication](<https://devfeed.tech/tags/communication.md>), [culture](<https://devfeed.tech/tags/culture.md>), [growth](<https://devfeed.tech/tags/growth.md>)

### AI overview

The author advocates assigning each software project to a named engineer who owns implementation, stakeholder communication, and decisions. Drawing on Nordhealth's experience, the article describes coaching engineers into this responsibility, supporting them when failures occur, and maintaining weekly written updates and leadership office hours.

### Source excerpt

Recently at Nordhealth we embarked on a re-skin of our entire application: a visual uplift of the whole product to bring it into 2026. These kinds of changes have a big blast radius and are inherently risky, but we championed the individuals to be bold, working across any surfaces that needed an uplift. Generally speaking, [...] The post Put a name on it appeared first on The Engineering Manager.

## How Rillet ships 3x faster with AI agents on Vercel

DevFeed: [How Rillet ships 3x faster with AI agents on Vercel](<https://devfeed.tech/articles/how-rillet-ships-3-faster-with-ai-agents-on-vercel-84351.md>)

Original publisher: [Read original article](<https://vercel.com/blog/how-rillet-ships-3-faster-with-ai-agents-on-vercel>)

Author: Susan Aziz

Published: 2026-10-09T04:00:00Z

Content type: article

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>), [Deployment-Driven Development](<https://devfeed.tech/topics/deployment-driven-development.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [enterprise-resource-planning](<https://devfeed.tech/tags/enterprise-resource-planning.md>), [erp](<https://devfeed.tech/tags/erp.md>), [eve](<https://devfeed.tech/tags/eve.md>), [framework](<https://devfeed.tech/tags/framework.md>), [ledger](<https://devfeed.tech/tags/ledger.md>), [linear](<https://devfeed.tech/tags/linear.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

Rillet reports tripling its shipping rate in three months after standardizing internal agents on eve and deploying them on Vercel. Its two-person frontend team says it closed more than 800 Linear tickets in four months; a customer success workflow captures requests in a Chrome extension, sends scoped changes to a coding agent to draft and implement, and returns a tested pull request with screenshots for human review. Rillet says its CPA team can ship some customer requests within two hours. eve groups instructions, tools, skills, and other agent components in directories, allowing behavior to be shaped with Markdown while tools use TypeScript; Vercel Connect provides runtime Slack and Linear access with short-lived tokens. AI Gateway lets builders select models by configuration string and see usage and costs. Enterprise Managed Users, SSO, and Directory Sync let Rillet manage builder accounts through its company identity provider. These are company-reported outcomes and workflows.

### Source excerpt

Rillet on Vercel Tripled shipping rate in three months with eve agents deployed on Vercel Two-person team closed 800+ Linear tickets in its first 4 months Builder access via Enterprise Managed Users, SSO, and Directory Sync Ships customer-requested changes to production in as little as two hours Gives every builder access to models through AI Gateway Rillet is an AI-native enterprise resource planning (ERP) platform. Their AI agents do accounting work inside a real-time general ledger, with human approval and a full audit trail. Rillet serves more than 600 customers working toward a zero-day close, reducing the time needed to close their books at month-end. A product that helps customers close their books in near real time needs a team that can respond quickly to their requests. Anthony Liang heads Rillet's two-person frontend team, formed only a few months ago, and leads the push to put agents to work across internal workflows, from shipping customer fixes to reviewing code. The team builds agents with eve and runs them on Vercel, using Vercel Connect to give them access to Slack and Linear, while AI Gateway routes their model requests. Standardizing every internal agent on eve Anthony had been building AI applications since the GPT-3.5 era and had evaluated nearly every agent framework on the market, from the major model providers' SDKs to the open-source ecosystem. Each gave him primitives for the model loop but left him to decide where instructions lived, how tools registered, and how an agent reached Slack and GitHub. Anthony could make those choices for his own agents, but he wanted conventions everyone at Rillet could follow, including people who had never touched TypeScript. An agent is a directory Anthony chose eve, Vercel's open-source agent framework for building, running, and scaling agents that keeps instructions, tools, and skills together in one directory. People who know what an agent should do can shape its behavior through markdown instructions and

## You can now chat with Lovable for free

DevFeed: [You can now chat with Lovable for free](<https://devfeed.tech/articles/you-can-now-chat-with-lovable-for-free-80763.md>)

Original publisher: [Read original article](<https://lovable.dev/blog/chat-for-free>)

Published: 2026-09-24T08:40:00Z

Content type: article

Language: en

Sources: [Lovable](<https://devfeed.tech/sources/lovable.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [announcements](<https://devfeed.tech/tags/announcements.md>), [app](<https://devfeed.tech/tags/app.md>), [building](<https://devfeed.tech/tags/building.md>), [chat](<https://devfeed.tech/tags/chat.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [idea](<https://devfeed.tech/tags/idea.md>), [like](<https://devfeed.tech/tags/like.md>)

### AI overview

Lovable introduces a free daily chat allowance for exploring app ideas, reviewing customer feedback, planning product changes, and working with existing apps. The article says Lovable can inspect app code and database usage, draft related work materials, and build changes; image or video generation and handoffs to Plan or Build still use credits.

### Source excerpt

You can now chat with Lovable for free. Ask it which idea is worth building. Have it turn customer feedback into a plan. Put it to work on an app you've already launched.

## What is WorkOS Airlock? Intent-based access control for AI agents

DevFeed: [What is WorkOS Airlock? Intent-based access control for AI agents](<https://devfeed.tech/articles/what-is-workos-airlock-intent-based-access-control-for-ai-agents-58820.md>)

Original publisher: [Read original article](<https://workos.com/blog/workos-airlock>)

Author: WorkOS

Published: 2026-09-23T16:46:32Z

Content type: tutorial

Language: en

Sources: [WorkOS](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [API](<https://devfeed.tech/topics/api.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [OAuth](<https://devfeed.tech/topics/oauth.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [gmail](<https://devfeed.tech/tags/gmail.md>), [linear](<https://devfeed.tech/tags/linear.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [requirements](<https://devfeed.tech/tags/requirements.md>)

### AI overview

This guide explains how WorkOS Airlock applies intent-based access control to AI agent calls. It describes how Airlock works with WorkOS Pipes, OAuth-connected tools such as Linear and Gmail, declared intent, and policies that govern API operations and content before calls proceed.

### Source excerpt

What is WorkOS Airlock? See how intent-based access control governs AI agent calls, where Pipes fits, and how the email demo turns policy into action.

## How Warp ships 2,000 PRs a month with AI factories | Zach Lloyd (CEO, Warp)

DevFeed: [How Warp ships 2,000 PRs a month with AI factories | Zach Lloyd (CEO, Warp)](<https://devfeed.tech/articles/how-warp-ships-2-000-prs-a-month-with-ai-factories-zach-lloyd-ceo-warp-57545.md>)

Original publisher: [Read original article](<https://www.lennysnewsletter.com/p/how-warp-ships-2000-prs-a-month-with>)

Author: Claire Vo

Published: 2026-09-21T12:04:11Z

Content type: article

Language: en

Sources: [Lenny's Newsletter](<https://devfeed.tech/sources/lenny-s-newsletter.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Software](<https://devfeed.tech/topics/software.md>), [Warp](<https://devfeed.tech/topics/warp.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [automation](<https://devfeed.tech/tags/automation.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [github](<https://devfeed.tech/tags/github.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [integration](<https://devfeed.tech/tags/integration.md>), [issue-tracking](<https://devfeed.tech/tags/issue-tracking.md>), [linear](<https://devfeed.tech/tags/linear.md>), [llm](<https://devfeed.tech/tags/llm.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [slack](<https://devfeed.tech/tags/slack.md>), [software](<https://devfeed.tech/tags/software.md>), [team](<https://devfeed.tech/tags/team.md>), [warp](<https://devfeed.tech/tags/warp.md>)

### AI overview

A podcast episode featuring Warp CEO Zach Lloyd explains how Warp's AI software factory turns requests from Slack, Linear, and GitHub into tracked, tested pull requests. It covers automation, human review, agent-run evaluation, failure analysis, and cost-quality tradeoffs in AI-assisted software delivery.

### Source excerpt

Watch now (47 mins) | 🎙 Warp CEO Zach Lloyd shows how his team turns requests from Slack, Linear, and GitHub into tracked, tested pull requests, then measures and improves its cloud-based AI software factory over time

## Adopting the software factory pattern with AI coding agents

DevFeed: [Adopting the software factory pattern with AI coding agents](<https://devfeed.tech/articles/trying-the-software-factory-pattern-55599.md>)

Original publisher: [Read original article](<https://lethain.com/software-factory-experiment/>)

Published: 2026-09-20T12:00:00Z

Content type: opinion

Language: en

Sources: [Irrational Exuberance](<https://devfeed.tech/sources/irrational-exuberance.md>), [Will Larson - Irrational Exuberance](<https://devfeed.tech/sources/will-larson-irrational-exuberance.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [task management](<https://devfeed.tech/topics/task-management.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Scalability](<https://devfeed.tech/topics/scalability.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [linear](<https://devfeed.tech/tags/linear.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>)

### AI overview

The article describes an evolving 2026 adoption process for AI-assisted software development, including Claude Code, Claude Cowork, independent workspaces, cross-repository pull requests, Linear, and an orchestrated agent harness. It then outlines an initial software factory implementation that uses an agent skill, project documentation, metrics, and task updates to pursue broad goals.

### Source excerpt

One of the interesting challenges of the AI ecosystem in 2026 is that new, effective patterns emerge faster than I can adopt them. I'll find a handful, get back to work, and realize a month later that I'd missed four or five more. The adoption cycle for Imprint this year has been something like: January: get every engineer onto Claude Code every single day March: ok, let's also get everyone else onto Claude Code or Claude Cowork every single day April: local development is bottlenecked on checkout and worktree model, instead create ~10 local workspaces which each have an independent checkout of every repository, and operate at the workspace level, not at the repository level, so it can generate cross-repository pull requests across frontend, backend, infrastructure and data monorepos June: oh boy, agent-driven development is heavily constrained by lack of a common task management system with higher visibility and less permission complexity than Jira, so let's migrate the entire company over to Linear and hard stop on Jira July: yikes, now we have visibility into all these tickets, many of them are trivial but managing them through local development isn't scaling, let's roll out an orchestrated harness which internally we call "Agent Fleet", along the lines of Stripe's Minions The most recent question for me has been figuring out how to adopt the software factory pattern. (After some light research, the specific AI-context origin of this term is slightly messy to attribute, but I think it might be Justin McCarthy in February 2026's Software Factories And The Agentic Moment.) The software factory pattern is looping on a broad goal, and then relying on the harness to drive progress towards that goal. Our first pass at implementation is fairly basic: An agent skill /linear-project-loop which reads in a Linear project and starts by auditing that project's goal definition on these dimensions: An RFC in Notion that describes the project's goals, how those goals are measure

## Have 1 Goal, Not 10

DevFeed: [Have 1 Goal, Not 10](<https://devfeed.tech/articles/have-1-goal-not-10-55109.md>)

Original publisher: [Read original article](<https://www.thesweekly.com/p/the-less-you-want-the-more-you-can>)

Author: Kevin Naughton Jr.

Published: 2026-09-18T13:30:44Z

Content type: opinion

Language: en

Sources: [The Software Engineer Weekly](<https://devfeed.tech/sources/the-software-engineer-weekly.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [linear](<https://devfeed.tech/tags/linear.md>), [product](<https://devfeed.tech/tags/product.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

The author argues that pursuing one carefully chosen goal requires sustained focus and reducing the flow of distracting information. They connect this approach to consistently working on Ferryman, using Linear to prioritize feature work and tracking the product's progress through Stripe MRR.

### Source excerpt

I believe that if you want one thing in life and really focus on achieving it, you can almost always get it. If you believe this too, and are willing to work long enough and hard enough to eventually achieve it, the most important task then becomes choosing the right goal.

## Sharing Linear's growth with the people building it

DevFeed: [Sharing Linear's growth with the people building it](<https://devfeed.tech/articles/sharing-linear-s-growth-with-the-people-building-it-83580.md>)

Original publisher: [Read original article](<https://linear.app/now/sharing-growth-with-the-people-building-linear>)

Published: 2026-08-26T11:43:06Z

Content type: article

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>)

Tags: [accel](<https://devfeed.tech/tags/accel.md>), [accelerated](<https://devfeed.tech/tags/accelerated.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [growth](<https://devfeed.tech/tags/growth.md>), [hiring](<https://devfeed.tech/tags/hiring.md>), [issue-tracking](<https://devfeed.tech/tags/issue-tracking.md>)

### AI overview

Linear describes a $99 million tender offer that let current and former employees sell some vested equity at a $2.5 billion valuation. The company says it is cashflow positive, has passed $100 million in annual recurring revenue, and is expanding its agent platform for product development. It reports that agents are installed in 95% of paid workspaces and generate half of newly created work, while sharing plans to hire across several functions.

### Source excerpt

As Linear passes $100 million in ARR, we're giving our team another opportunity to participate in the upside.

## LangSmith Engine Improves Agent Issue Detection by 2x

DevFeed: [LangSmith Engine Improves Agent Issue Detection by 2x](<https://devfeed.tech/articles/langsmith-engine-improves-agent-issue-detection-by-2x-78341.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/new-in-langsmith-engine-2x-better-issue-detection>)

Author: LangChain Accounts

Published: 2026-08-25T19:38:39Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [engine](<https://devfeed.tech/tags/engine.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [linear](<https://devfeed.tech/tags/linear.md>), [slack](<https://devfeed.tech/tags/slack.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

LangSmith Engine analyzes production agent traces to identify and group issues, diagnose root causes, propose prompt or code fixes, and monitor for regressions. This release reports more than twice the performance on internal issue detection benchmarks and 25% better results on industry benchmarks for fixes. It also adds Slack alerts, Linear issue creation, self-hosted deployment support, reduced analysis for cost control, and automatic cleanup of stale issues. Automated fix verification and dataset generation are described as future work.

### Source excerpt

LangSmith Engine now detects agent issues over 2x better, proposes stronger fixes, supports Slack and Linear workflows, and is available for self-hosted deployments.

## When non-devs open PRs

DevFeed: [When non-devs open PRs](<https://devfeed.tech/articles/when-non-devs-open-prs-32338.md>)

Original publisher: [Read original article](<https://newsletter.manager.dev/newsletter/when-non-devs-open-prs>)

Author: Anton Zaides

Published: 2026-08-25T06:01:00Z

Content type: opinion

Language: en

Sources: [Manager.dev](<https://devfeed.tech/sources/manager-dev.md>)

Topics: [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [code](<https://devfeed.tech/tags/code.md>), [jira](<https://devfeed.tech/tags/jira.md>), [linear](<https://devfeed.tech/tags/linear.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

An opinion article examines the challenges and potential benefits of allowing non-engineers, including product managers and designers, to open pull requests on a software codebase. It discusses review responsibility, boundaries, scaling concerns, and reduced communication cycles, while citing Linear usage data about non-engineer code contributions and AI feature use.

### Source excerpt

What to watch out for when letting non-engineers open PRs on your codebase

## Automating quality support at scale: AI and human in the loop

DevFeed: [Automating quality support at scale: AI and human in the loop](<https://devfeed.tech/articles/automating-quality-support-at-scale-ai-and-human-in-the-loop-30723.md>)

Original publisher: [Read original article](<https://www.windmill.dev/blog/support-automation>)

Author: Hugo Casademont

Published: 2026-08-18T00:00:00Z

Content type: article

Language: en

Sources: [Windmill Blog](<https://devfeed.tech/sources/windmill-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Discord](<https://devfeed.tech/topics/discord.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [GitHub Issues](<https://devfeed.tech/topics/github-issues.md>), [email](<https://devfeed.tech/topics/email.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [WebSocket](<https://devfeed.tech/topics/websocket.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-windmill-support-claude](<https://devfeed.tech/tags/ai-windmill-support-claude.md>), [automated](<https://devfeed.tech/tags/automated.md>), [claude](<https://devfeed.tech/tags/claude.md>), [discord](<https://devfeed.tech/tags/discord.md>), [email](<https://devfeed.tech/tags/email.md>), [github-issues](<https://devfeed.tech/tags/github-issues.md>), [linear](<https://devfeed.tech/tags/linear.md>), [slack](<https://devfeed.tech/tags/slack.md>), [support](<https://devfeed.tech/tags/support.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [windmill](<https://devfeed.tech/tags/windmill.md>)

### AI overview

Windmill describes an internal support-automation pipeline that consolidates Discord, Slack, email, and GitHub issues into a Discord queue. It uses Claude and customer context to triage requests, draft replies and fixes, while requiring human approval before responses are sent.

### Source excerpt

How does Windmill automate its own support? A Windmill pipeline funnels Discord, Slack and email tickets into one Discord queue, triages them with Claude, drafts replies, and dispatches fixes.

## Groundcover connects observability agents to Slack, Linear, and team context

DevFeed: [Groundcover connects observability agents to Slack, Linear, and team context](<https://devfeed.tech/articles/meet-groundcover-put-agent-mode-to-work-where-your-team-already-works-80066.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/meet-groundcover>)

Author: Anais Dotis

Published: 2026-08-13T19:50:00Z

Content type: article

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [telemetry](<https://devfeed.tech/topics/telemetry.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [groundcover](<https://devfeed.tech/tags/groundcover.md>), [linear](<https://devfeed.tech/tags/linear.md>), [logs](<https://devfeed.tech/tags/logs.md>), [root-cause-analysis](<https://devfeed.tech/tags/root-cause-analysis.md>), [slack](<https://devfeed.tech/tags/slack.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

Groundcover describes first-class connectors that let its observability agent use organizational context from tools such as Slack, Linear, Cursor Cloud Agents, and Notion alongside telemetry. The agent can investigate alerts, build dashboards, and create Linear tickets, with controls to allow, require approval for, or block specific actions. The article demonstrates an incident workflow in which the agent analyzes telemetry, requests approval before creating a ticket, and records a root cause analysis.

### Source excerpt

Learn about how to set up the Slack and Linear connector with groundcover to use the groundcover agent directly in Slack to retrieve logs, traces, monitor issues, dashboards, and even RUM. Then use the groundcover agent in Slack to perform root cause analysis and file Linear tickets.

## How we built Linear Agent

DevFeed: [How we built Linear Agent](<https://devfeed.tech/articles/how-we-built-linear-agent-83549.md>)

Original publisher: [Read original article](<https://linear.app/now/how-we-built-linear-agent>)

Published: 2026-08-10T12:19:00Z

Content type: article

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [cli](<https://devfeed.tech/tags/cli.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [linear](<https://devfeed.tech/tags/linear.md>)

### AI overview

Linear explains how it built Linear Agent to handle complex product tasks while limiting unpredictable behavior. The design uses focused system prompts, constrained tools, product-specific skills loaded as needed, contextual approval checks, and a custom harness for streaming, durable workflows, and asynchronous sub-agent execution. The team chose a narrower action surface to improve predictability and reduce mistakes, while retaining flexibility as models improve.

### Source excerpt

The product and engineering decisions we made so Linear Agent can handle complex tasks without becoming unpredictable.

## Copilot cloud agent for Linear is now generally available

DevFeed: [Copilot cloud agent for Linear is now generally available](<https://devfeed.tech/articles/copilot-cloud-agent-for-linear-is-now-generally-available-71576.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-07-23-copilot-cloud-agent-for-linear-is-now-generally-available>)

Author: Allison

Published: 2026-07-23T22:32:23Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>)

Tags: [cloud-agent](<https://devfeed.tech/tags/cloud-agent.md>), [github-actions](<https://devfeed.tech/tags/github-actions.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>)

### AI overview

GitHub announces general availability of its Copilot cloud agent for Linear. Users can assign Linear issues to the agent, which analyzes them, opens draft pull requests, works in an ephemeral development environment powered by GitHub Actions, and streams progress to Linear. Users can choose a model, configure custom agents and branches, and steer sessions through comments.

### Source excerpt

You can now assign issues in Linear to Copilot cloud agent, our asynchronous, autonomous background agent. When you assign a Linear issue to Copilot, it will: Analyze the issue contents...

## Multi-select fields for Projects and Issues in public preview

DevFeed: [Multi-select fields for Projects and Issues in public preview](<https://devfeed.tech/articles/multi-select-fields-for-projects-and-issues-in-public-preview-71579.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-07-23-multi-select-fields-for-projects-and-issues-in-public-preview>)

Author: Allison

Published: 2026-07-23T18:19:14Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [issue](<https://devfeed.tech/tags/issue.md>), [modules](<https://devfeed.tech/tags/modules.md>), [project](<https://devfeed.tech/tags/project.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

GitHub public preview adds multi-select fields to Projects and issues. Users can assign multiple values to one field, set them from the sidebar, and filter by them in project views.

### Source excerpt

You can now create multi-select fields in Projects and Issue fields so a single field can hold more than one value. Tag an item with everything it relates to (e.g.,...

## Introducing Loops

DevFeed: [Introducing Loops](<https://devfeed.tech/articles/introducing-loops-83558.md>)

Original publisher: [Read original article](<https://linear.app/now/introducing-loops>)

Published: 2026-07-20T15:30:00Z

Content type: release

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Product Management](<https://devfeed.tech/topics/product-management.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [developer-workflows](<https://devfeed.tech/tags/developer-workflows.md>), [linear](<https://devfeed.tech/tags/linear.md>), [loop-engineering](<https://devfeed.tech/tags/loop-engineering.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [product-development](<https://devfeed.tech/tags/product-development.md>)

### AI overview

Linear is launching Loops, recurring AI workflows that run on a schedule or in response to events across a team's workspace. Teams can use them to triage bug reports, create follow-up issues, and update project plans, with shared visibility into each run.

### Source excerpt

Loop engineering has quickly emerged as an important practice in software development. In tools like Claude Code and Codex, developers define recurring or trigger-based behavior for their agents, usually through a /loop command, and hand off the repetitive tasks that would otherwise consume their attention. The resulting productivity gains are real, but so far they have mostly been limited to individual developer workflows. What if an entire product team could work this way? The opportunity is everywhere. Product development is full of repetitive operational work that requires a human in the loop: an engineer needs to understand every incoming bug report and investigate a project manager needs to notify teams affected by scope changes as they happen a marketer needs to update the launch schedule as target dates shift These processes are usually well understood, but someone still has to monitor incoming changes, apply judgement, and take action. That's why today we're launching Loops, a new way for Linear Agent to take on recurring work across your team. Loops let you define scheduled or event-driven operations for Linear Agent to run across your workspace. Because they operate natively inside Linear, they can work from the full context of your issues, projects, documents, and connected tools, while remaining visible and controllable by your teams. The result is a practical way to offload product operations and keep important work moving without constant oversight. How Loops work To set up a Loop, describe the job in plain language and then choose whether it should run on a schedule or in response to an event. Each time a loop runs, Linear Agent reviews its instructions and determines what should happen next. It can draw on context from Linear, connected codebases, MCP servers, and previous runs. Because Loops are fully AI-powered, they can apply judgment as they work. They can account for exceptions, navigate ambiguity, gather missing information, and decide on the

## Teaching an agent to auto-fix bugs

DevFeed: [Teaching an agent to auto-fix bugs](<https://devfeed.tech/articles/teaching-an-agent-to-auto-fix-bugs-83561.md>)

Original publisher: [Read original article](<https://linear.app/now/linear-agent-bug-fix>)

Published: 2026-06-12T16:34:00Z

Content type: article

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [Linear](<https://devfeed.tech/topics/linear.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [bugfixes](<https://devfeed.tech/topics/bugfixes.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [ai code review](<https://devfeed.tech/topics/ai-code-review.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [linear](<https://devfeed.tech/tags/linear.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [triage](<https://devfeed.tech/tags/triage.md>), [types](<https://devfeed.tech/tags/types.md>)

### AI overview

A Linear engineer describes automating bug triage with Linear Agent. The agent handles well-scoped dead feature flag cleanup reliably, while fixes for variable background task failures succeed less often; added gates reduce unsuitable pull requests, and the agent can still investigate issues it cannot fix. The article emphasizes providing task context through workflow skills, automation rules, code conventions, and review.

### Source excerpt

I was very skeptical of AI to begin with. Part of me suspected the technology wasn't as capable as the hype would suggest, while another part was deeply worried that it was far more capable than I wanted to admit. But the closer I got to the technology the more those worries started to fade. The tech is very capable, but when you work with it you start to realise the extent of that capability. Where it's strong, where it's weak, and how the engineering role is evolving to fit the spaces between them. I've spent the majority of my time over the past few months building out automations in Linear. When combined with the Linear Agent, which can read and write code, and take actions in your workspace, you get an outcome that's close to what we described last year as "Self-driving SaaS". Software that can do things in the background on your behalf, moving work forward, guided by rules and gates rather than a human hand. How much it can own from start to finish varies enormously depending on how your team works and what your codebase looks like, it's not a fixed property of the technology. We've had to experiment a lot to find the edges of that capability and then work back. An automation I've been experimenting with lately is getting the Linear Agent to auto-fix bugs that land in triage. When we first tried this workflow we had the agent attempt a first pass at all the bugs coming in. That didn't work very well because there wasn't enough context to one-shot the fix, so we had to narrow the ask and feed it the right instructions and tools. There are two types of issues that the agent is good at fixing on the first pass in our workspace today: catching dead feature flags and patching up failing background tasks. Automations I've been building Through our Datadog integration, a monitor catches the problem and files an issue into triage, where an automation assigns it to the Linear Agent to pick up, run the relevant skill, and take a pass. Dead feature flags are the cleaner

## Linear launches coding sessions, automated triage, and code review for Linear Agent

DevFeed: [Linear launches coding sessions, automated triage, and code review for Linear Agent](<https://devfeed.tech/articles/now-linear-writes-the-code-too-83537.md>)

Original publisher: [Read original article](<https://linear.app/now/coding-sessions-for-linear-agent>)

Published: 2026-06-11T18:25:29Z

Content type: release

Language: en

Sources: [Linear](<https://devfeed.tech/sources/linear.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Code review](<https://devfeed.tech/topics/code-review.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [linear](<https://devfeed.tech/tags/linear.md>), [product](<https://devfeed.tech/tags/product.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [review](<https://devfeed.tech/tags/review.md>)

### AI overview

Linear Agent adds coding sessions that let it take an issue through investigation, implementation, and pull request creation in a shared cloud workflow. Automated triage can start that process when issues arrive, while Diffs supports code review in Linear. Teams can supply context, redirect the agent, and choose how much of the process to automate.

### Source excerpt

Agents are becoming capable of doing more of the work involved in building software, but they're still mostly individual productivity tools, useful to one person at a time. Building a product is something a team does together, and the work that goes into it, like the decisions and the reasoning behind them, forms the context the whole product is built on. That context rarely lives in one place. It accumulates across Linear issues, documents, Slack threads, and code, which is why we've worked to bring more of product development into Linear and pull it all together. Linear Agent can draw on all of it. We've given it skills and automations so it follows how your team works, and MCP to reach the rest of your stack. It can read your codebase with Code Intelligence and help you review code changes with Diffs. But the loop wasn't complete. The coding work itself still happened somewhere else, so an engineer had to take the context from Linear, restate it inside another tool, monitor the work, and bring the result back for review. Today, we're launching coding sessions, automated triage, and Diffs to bring execution into the same shared system. Coding sessions Coding sessions let Linear Agent natively move directly from an issue to implementation. You can delegate an issue to the agent, ask it to fix something, or @mention it from Slack or Teams. The agent reads the issue and its surrounding discussion, investigates the codebase, proposes an approach, writes the code, and opens a pull request. This all happens in the cloud, using frontier models and harnesses like Claude Code or Codex. The coding session starts with the context already connected to the issue: the original request, customer signal, product decisions, related work, and discussion. Nobody needs to gather this information and reconstruct it inside a new prompt. The session is also shared with the team. Anyone can follow the work, contribute context, redirect the approach, request changes, or take over. The ses

[Next page](<https://devfeed.tech/topics/linear.md?cursor=WyIyMDI2LTA2LTExVDE4OjI1OjI5KzAwOjAwIiwgIjk0NTVhOTk4LTU1YjctNDZhZC05NjI4LTZmNzMxZWY1MDA1YSJd>)