Code Intelligence. Linear can understand, answer questions about, and debug your codebase.
Code Diffs. Review code within a fast, modern interface built for both humans and agents to iterate together.
Linear Coding Agent. Linear writes code and automatically fixes bugs. Powered by frontier models, enhanced with native Linear context and tools
So another wrapper around Claude/OpenAI but with issue tracking integrated.
Agents are not mind readers. They become useful through context. Customer feedback, internal ideas, strategic direction, decisions, and code all need to be captured in a system that humans and agents can work from together.
Customer feedback can come from anywhere, phone calls, website forms, sales people, customer meetings, online discussions, Twitter, etc. How do you capture all of that in Linear? Doesn't make sense.
Internal ideas and strategic direction are usually discussed on Slack/Teams/meetings. Not on Linear.
Decisions can indeed be tracked on Linear, as an issue.
I think a true AI agent would simply sidestep tools like Linear. Tools like Linear won't be needed.
I think a true AI agent will simply be another employee. It gets added to Slack channels. It joins Zoom meetings. It gets access to company files. It gets access to feedback forms. It scours the internet for feedback on the company.
> Linear is the shared product system that turns context into execution.
I agree it’s weird, but this is a pattern many companies are applying. They’re desperate to look like an AI company and to centralize themselves as the place where everything happens. It helps with investors and some customers.
But yes I think having agents in these products is weird - and most people would rather access the basic features / data via their own agent of choice, outside these products.
At ZAR once we had pervasive ingestion into an organization-wide knowledge graph in place and working well, the next step was to ditch Linear and replace it with a homegrown experiment tracking system that focuses all product engineers on empirical data and scientific method applied to how we prioritize work.
It's the only way to actually encourage high-agency, high-ownership behavior. Working from a backlog is actively counterproductive!
This feels awkwardly premature and dubious. I think "we're adding features to support better context modelling and execution with LLMs" would have sufficed.
I've thought of Linear as a careful, measured, thoughtful company in the past so this seems out of the blue, like there's some kind of existential crisis occurring over there.
> like there's some kind of existential crisis occurring over there
If you're running a Saas, especially a SaaS whose market is developers, and you're NOT having an existential crisis in 2026, the only possible explanation is you're asleep or possibly already dead.
Look, Linear, I like you. I currently use you. You're the best of a shitty bunch.
If you keep going down this track, you will enshittify your product and make those of us who just want a goddamn issue tracker, to start looking elsewhere for what feels like the millionth time.
Classic clickbait title. I guess it works, but also baits me to respond to it in the first paragraph: Issue tracking is clearly not dead, it is more important than ever.
They are doing almost everything right: I believe that this mode of control is exactly the future (use the chat for more complex natural language manipulation while seeing the result in the traditional UI).
> Code Diffs. Review code within a fast, modern interface built for both humans and agents to iterate together.
I really want to see diffs right in the issue. PRs are a dumb historically grown in-between step that is just annoying. As everything else becomes faster, this becomes more of a bottleneck for iteration speed.
> Linear Coding Agent. Linear writes code and automatically fixes bugs. Powered by frontier models, enhanced with native Linear context and tools.
Is this supposed to replace my dedicated coding agent? I’m skeptical of coding agents being built as parts of other products. It feels like an afterthought, 80% solution - not good enough for real intense use.
If it has very tight HITL (possibly integrated right into the ticket - that would be amazing), it might be really good - they are in a unique position to build an amazing product here.
Issue tracking is not only not dead, it’s a more structured way to handle your agents.
I just know my previous job will eat this up. They're generating tickets, PRs and Reviews nowadays. I have no idea what the quality looks like, but I doubt it's anything but good.
The amount they ask customers does not match their output
11 comments
[ 2.6 ms ] story [ 24.8 ms ] threadInternal ideas and strategic direction are usually discussed on Slack/Teams/meetings. Not on Linear.
Decisions can indeed be tracked on Linear, as an issue.
I think a true AI agent would simply sidestep tools like Linear. Tools like Linear won't be needed.
I think a true AI agent will simply be another employee. It gets added to Slack channels. It joins Zoom meetings. It gets access to company files. It gets access to feedback forms. It scours the internet for feedback on the company.
I agree it’s weird, but this is a pattern many companies are applying. They’re desperate to look like an AI company and to centralize themselves as the place where everything happens. It helps with investors and some customers.
But yes I think having agents in these products is weird - and most people would rather access the basic features / data via their own agent of choice, outside these products.
It's the only way to actually encourage high-agency, high-ownership behavior. Working from a backlog is actively counterproductive!
I've thought of Linear as a careful, measured, thoughtful company in the past so this seems out of the blue, like there's some kind of existential crisis occurring over there.
If you're running a Saas, especially a SaaS whose market is developers, and you're NOT having an existential crisis in 2026, the only possible explanation is you're asleep or possibly already dead.
If you keep going down this track, you will enshittify your product and make those of us who just want a goddamn issue tracker, to start looking elsewhere for what feels like the millionth time.
They are doing almost everything right: I believe that this mode of control is exactly the future (use the chat for more complex natural language manipulation while seeing the result in the traditional UI).
> Code Diffs. Review code within a fast, modern interface built for both humans and agents to iterate together.
I really want to see diffs right in the issue. PRs are a dumb historically grown in-between step that is just annoying. As everything else becomes faster, this becomes more of a bottleneck for iteration speed.
> Linear Coding Agent. Linear writes code and automatically fixes bugs. Powered by frontier models, enhanced with native Linear context and tools.
Is this supposed to replace my dedicated coding agent? I’m skeptical of coding agents being built as parts of other products. It feels like an afterthought, 80% solution - not good enough for real intense use.
If it has very tight HITL (possibly integrated right into the ticket - that would be amazing), it might be really good - they are in a unique position to build an amazing product here.
Issue tracking is not only not dead, it’s a more structured way to handle your agents.
The amount they ask customers does not match their output