How Intercom 2x'd their engineering velocity in 9 months with Claude Code lennysnewsletter.com
Brian Scanlan, a senior principal engineer at Intercom, talking to Claire Vo on “How I AI”. This is a podcast episode page rather than a written account, so the detail comes from the episode summary and transcript rather than an engineering write-up.
The headline number is narrower than the title suggests. What doubled in nine months was merged PRs per R&D employee, not output or delivered value, and a merged PR is a unit that AI tooling makes easier to produce in quantity. Worth holding that in mind before reading it as a doubling of engineering velocity. Alongside it: 100% of engineers, plus designers, PMs and TPMs, now ship code via Claude Code.
The parts that travel better than the metric are the supporting machinery. Intercom built a skills repository whose hooks enforce engineering standards automatically, and telemetry through Honeycomb to track skill usage, adoption and quality across hundreds of engineers, so claims about what AI is doing to the codebase can be checked rather than asserted. Scanlan also argues that backlog zero is now achievable, and that the product itself needs preparing for an agent-first world through CLIs, MCPs and ephemeral APIs.
See also Intercom on letting AI approve PRs and Fin on good skills and bad skills.