Separate product development into two phases. The problem-finding and decision-making phase should remain slow and deliberate to ensure quality. However, once a decision is committed, AI tools should be leveraged to make the execution and feedback loops as fast as possible.
While AI can accelerate prototyping, Linear's CEO deliberately uses a manual, slower design process for initial exploration. The friction of drawing things manually forces self-reflection and a deeper understanding of the problem, a benefit that can be lost when optimizing purely for speed.
Linear believes AI coding agents remove any excuse for having bugs in a product. They implement a 'zero bugs' policy with a one-week fix SLA. AI agents can now perform the initial triage and even attempt a fix, then tag an engineer for review, dramatically accelerating bug resolution.
Measuring AI's impact by output metrics like 'percent of agent-written code' or 'number of PRs merged' is a trap. These metrics say nothing about value. Instead, focus on counterbalance metrics that measure quality and meaningful impact, such as a reduction in bugs or positive user feedback.
Linear doesn't try to build a better general-purpose coding agent than Google or OpenAI. Instead, its strategic advantage is sitting 'upstream' where work originates. By integrating agents into the initial bug report or feature request, they can automate the entire workflow, a defensible moat.
The idea that AI will kill SaaS is too simplistic. It most accurately applies to large, public companies with significant inertia whose existing moats are disappearing. Startups and growth-stage companies that can maintain a 'day one' mentality and constantly re-evaluate their product have a significant advantage.
While Linear started by creating a platform for third-party agents, they found they couldn't control or improve the end-to-end user experience. This limitation prompted them to build their own coding agent to create a smoother, more integrated workflow where context is automatically injected.
Most AI tools are single-player experiences. Linear is designing its agent sessions to be shared, collaborative spaces. Multiple people, like a PM and a designer, can jump into the same chat with an agent, see its work, and give it feedback together, collapsing the collaboration loop.