Linear

Introducing coding sessions. Linear Agent can now triage issues, investigate the cause, write the fix, open a PR, and bring the code back for review. All shared with your team in Linear.

Also new this week: • Desktop navigation history and pinned tabs • Private sub-teams • Release pipeline changelogs Learn more: linear.app/changelog/2026…

New: Agent assisted project updates 1. From an update, click Write with Agent 2. Linear drafts an update based on recent activity and Slack conversations 3. Verify, iterate, and post

@143_qi Thanks for the feedback and workflow description too, we've filed a feature request to consider this, if anything changes we'll follow-up with you here. We really appreciate your feedback - Thank You!

@linear guys please allow us to copy issue links as markdown in the mobile app too 🙏🙏

Quality of life improvement: Settings search.

@MankyBansal Not seeing this on our side. Can you drop a note into support@linear.app? We'll dig into it.

yo @linear, file drag/drop on web comments has been broken for weeks, please fix

@A4rjun ⌘+K "Open settings"

@linear Can this be done from the command menu?

@HenryHaefliger Team is investigating the errors with more detail on our status page — we've reverted a suspected root cause and things should be more stable with a refresh linearstatus.com

Clicking any PR notification in the @linear app right now causes it to immediately crash

3/4 of these companies are having incidents or major app breakages right now. Says a lot about building with AI but zero testing. @OpenAI @linear @cognition do any of you want to try Momentic?

@danlucraft Details here; #pull-request-preview-links" target="_blank" rel="nofollow noopener">linear.app/docs/github#pu…

@karrisaarinen @linear This preview link, it's an internal-only Linear feature, right?

The software factory is humming along in @linear. An issue comes in from Intercom to Triage. Linear routes and categorizes it, investigates, opens a coding session, and has a fix ready for review 10 minutes later. We’re now merging 50 to 70 Linear agent generated fixes per week just from Triage. (Usage is priced with clear token-based credits. No monthly AI fees, no expiring credits.)

@farazKhan404 Should be already fixed, is it still happening on latest update?

@karrisaarinen @linear Probably on your radar but can't launch the app on the latest iOS beta! Keen to try this out 😊

Been enjoying @linear Agent and coding sessions on mobile. Going from a user question or bug report to a fix in minutes, then reviewing the diff and opening a PR right from your phone

@ft_sidd Thanks for the feedback, folders for organizing team documents would be a great addition, and we’ve shared this with the team! We'll follow-up here if we have some news on that to share. Thanks again Siddhant!

can we get folders to manage team documents on @linear please?

@vvedantb @hugorcd Yes, if your PR has a deployment preview URL, Diffs surfaces it via the "Preview" button so you can open and test the changes.

@hugorcd @linear Can you preview the changes it makes in a live dev server though?

I just tried @linear Diff. Genuinely speechless. The UI is so fucking good. Everything flows, it's beautiful, the AI makes sense, this is ridiculously perfect. I've been staring at it for 10 minutes, just appreciating how well it's designed

@b73127087 You can connect MCP servers to the Linear agent here; linear.app/settings/accou…

@linear Can Claude access figma mcp in this workflow?

Introducing coding sessions. Linear Agent can now triage issues, investigate the cause, write the fix, open a PR, and bring the code back for review. All shared with your team in Linear.

@ianhaz Taking a look into fixing, thanks for the report.

@linear how come I can't make the desktop app full screen in macOS anymore?

@0xfluke We hear you and added you to that feature request.

@linear Please add a search_document MCP tool that does semantic search across documents. I want to use the documents but it's token intensize to search for stuff.

@dariusparzygnat Sorry for the trouble here. Could you please email support@linear.app so we can take a closer look?

@linear why do i have to reconnect codex so often? i’ve never had this issue with github.

Following the US government's export control directive and Anthropic’s recent announcement, we are suspending access to Claude Fable 5 in Linear Agent’s coding sessions. To ensure minimal disruption, all workspaces who have enabled Claude Fable 5 are being automatically failed over to Claude Opus 4.8. We will provide updates as they become available.

@Damirofficial87 @karrisaarinen Yep - assign the issue to Linear and it’ll start automatically, provided coding sessions are enabled. You can also mention @linear in a comment with instructions.

@karrisaarinen @linear How do I prompt Linear agent to fix my issue in the backlog? Do I just assign the issue to Linear agent and he will pick up automatically? @karrisaarinen

Internally at @linear, the agent created and merged 700 PRs last month. Often fixing bugs automatically from triage.

@michellejmayes This is on our radar - for now, start the session by sending only owner/repo or the repository’s GitHub URL.

@linear I like coding agent sessions but sometimes it randomly picks the wrong repo and there's nothing I can do to fix it. The session and credits are gone. How can I deterministically make it pick the right repo without adding a comment "repo: X" ?

Linear Agent can now write code. We put it to work, automatically fixing bugs as they land in triage. Igor, the engineer behind these automations, shares how he set them up. linear.app/now/linear-age…

@Ferbin08 @karrisaarinen We have all of that and more: linear.app/security

@karrisaarinen @linear Enterprise SSO, audit logs, compliance at scale. That's the hard part, and Linear's still playing catch-up. By the time they ship that fully, it's just Jira with a better UI.

When we started @linear, we wanted to make product work feel more coherent across the whole team. Agents can now do more of the work, but too often they operate from an empty prompt, in isolation, for one person at a time. That risks creating a new layer of fragmentation. We think the larger shift happens when agents work from the same context as the team. With the new coding sessions, Linear Agent can now move from intake to investigation, code, and review inside that shared environment. This completes the product development loop we’ve been building toward: from intake to merge, with the team’s context intact.