Claire Vo · 2 min read · AI & Product
How Intercom 2x’d their engineering velocity in 9 months with Claude Code | Brian Scanlan
Read the original on lennysnewsletter.com →
Intercom doubled their R&D throughput in nine months by shipping with Claude Code across engineers, designers, PMs, and TPMs. They built telemetry to measure AI adoption and quality, plus a skills repository with automatic standards enforcement, and prepared for an agent-first product world with CLIs, MCPs, and ephemeral APIs—all under a permission and accountability framework that sustains AI-led velocity without sacrificing quality.
Key Takeaways
- Claude Code enabled significant acceleration, doubling merged PRs per R&D head and enabling cross-functional teams to ship more rapidly.
- Telemetry infrastructure (Honeycomb) was built to measure AI adoption, usage, and quality across hundreds of engineers.
- A skills repository with hooks automatically enforces engineering standards, ensuring consistent AI-enabled development.
- Agent-first tooling (CLIs, MCPs, ephemeral APIs) and a robust permission framework prepared product teams for AI-driven workflows while supporting backlog-zero culture.
Excerpt
Brian Scanlan is a senior principal engineer at Intercom, where he’s led the company’s transformation to AI-first engineering. In just nine months, Intercom doubled their R&D throughput while maintaining code quality, with 100% of engineers—plus designers, PMs, and TPMs—now shipping code via Claude Code. Listen or watch on YouTube , Spotify , or Apple Podcasts What you’ll learn: How Intercom doubled their merged PRs per R&D employee in just nine months using Claude Code The telemetry infrastructure they built to measure AI adoption and quality across hundreds of engineers Why they built a skills repository with hooks that enforce engineering…