Introducing Loops
Describe a recurring job in plain language and Linear Agent will run it on a schedule or in response to events, working from the full context of your workspace.
Boom Supersonic builds as fast as it flies
Boom Supersonic is bringing back supersonic flight before the end of the decade. To move that fast, its engineers borrowed the habits of software, building in short cycles and getting real parts in hand as quickly as they can.
Teaching an agent to auto-fix bugs
Some bugs at Linear now get fixed before a single engineer picks them up. Igor has been teaching Linear Agent to catch them in triage and ship the fix on its own.
Now Linear writes the code, too
Linear Agent can now write code. With Coding Sessions, it can take a bug from triage all the way to a reviewed fix, without the work ever leaving Linear.
Reviewing code in the agent era
Agentic coding has puts real pressure on review. One of our engineers shares how he uses Linear Diffs to hold his bar high without drowning in pull requests.
Code review should be fast
Agents are forcing a change in how we review code. Diffs brings code reviews directly inside Linear, so that the review lives alongside all of your product context.Changelog
Code Intelligence for Linear Agent
Linear Agent can now read your codebase and answer questions from the source itself.
Cars24’s push to being AI-native with Linear
In October, Cars24 renewed its Jira license. A few weeks later, they treated that contract as a sunk cost and walked away from it.
How we hire at Linear
Hiring well matters more than hiring fast. We’re happy to take our time, and believe each person who joins the team should raise the bar for the next one.
The coding agent behind 60% of Ramp’s merged PRs
Ramp’s internal coding agent now writes 60%+ of their merged PRs. With Linear as the underlying layer for structured product context, it can take on issues and work them to completion.
Output isn’t design
Design keeps being misunderstood in our industry. New tools keep promising to generate interfaces faster, move words to product instantly, or collapse design directly into code. The assumption behind them is clear: that design is the act of producing.
How we use Linear Agent at Linear
The workflows that proved most useful across CX, Product, and Engineering, and what they tell us about working with agents.Press
View all→
Post mortem on Linear security incident on March 24th, 2026
A code change temporarily weakened team-level permissions within some workspaces from 12:07 to 1:10 UTC (about one hour) due to a bug that caused a permission filter to be skipped.
Coinbase’s bet on agent-first development
In January 2026, Chintan asked his entire engineering organisation to delete their IDEs and write zero lines of code. For two weeks, every engineer at Base would have to do their job without touching a code editor.
Issue tracking is dead
The next era of product development is built on context and agency. Here's how Linear is evolving. And what we're launching today.
A calmer interface for a product in motion
The thinking, trade-offs, and tools behind our latest design refresh.
How Cursor builds with Linear
At Cursor, ideas don’t wait. Someone drops a potential feature in Slack, and by the time most teams would have scheduled a meeting, Cursor already has a branch open.
How Dandelion Chocolate scales craft
Dandelion Chocolate is a bean-to-bar chocolate maker based in San Francisco. As they scaled, the challenge was preserving their craft while building systems for growth.Archive
Design is more than codeHow our Customer Experience team works in LinearContinuous planning in LinearDesigning remote work at LinearSelf-driving SaaS: When software runs itselfA Linear spin on Liquid GlassBest practices for designing Linear DashboardsWhy we committed to a zero-bugs policyHow Commure uses Dashboards to track performance and guide planningHow we built Triage IntelligenceGiving our team liquidity through Linear’s first tender offerHow Cursor integrated with Linear for AgentsQuality Wednesdays: How we trained our team to see what doesn’t workOur approach to building the Agent Interaction SDK Inside Mercury’s six-month journey building with AI agents