How we use Linear Agent at Linear

Rhea Purohit walking through how Linear uses its own agent internally, told as three traced journeys rather than a feature list. A customer email arriving through Intercom becomes a scoped issue with the full back-and-forth attached, gets routed to the right team automatically, and ends with someone closing the loop with the customer. A Slack complaint becomes a scoped issue the agent then investigates using code intelligence and internal MCP servers. And a PM who noticed a missing filter while testing had the agent open both the issue and the pull request.

That third case is the interesting one, and it is more modest than it first looks: the PM’s pull request was still reviewed by a human engineer within the hour. The agent shortens the distance between noticing a problem and having a fix in review, rather than removing engineers from the path.

The stated lessons are that the best workflows keep the agent “close to the source” it needs context from, that “autonomy works best when it is introduced gradually”, and that agents earn their place at points of friction where work stalls. No figures are offered, and this is Linear describing its own product in use.