How Intercom 2x’d their engineering velocity in 9 months with Claude Code | Brian Scanlan

04/20/26
Source: Lenny’s Newsletter by Claire Vo. Read the original article

TL;DR Summary of How Intercom Doubled Their Merged PRs Per R&D Employee Using Claude Code

In just nine months, Intercom doubled their R&D throughput by adopting an AI-first engineering approach powered by Claude Code. The company established a robust telemetry infrastructure to measure AI adoption and maintain high code quality across all engineering roles. They also created a skills repository with automated standards enforcement, enabling rapid and consistent AI integration. This transformation supports an agent-first workflow that enhances productivity and engineering culture.

Optimixed’s Overview: Transforming Engineering Productivity with AI-Driven Workflows at Intercom

Intercom’s AI-First Engineering Revolution

Brian Scanlan, Senior Principal Engineer at Intercom, spearheaded a company-wide shift to embed AI deeply into engineering and product workflows. This transformation resulted in a remarkable increase in merged pull requests per R&D employee while preserving code quality. By integrating Claude Code, a cutting-edge AI coding assistant, Intercom enabled 100% of engineers, designers, product managers, and TPMs to contribute code efficiently.

Key Strategies and Technologies Implemented

  • AI Adoption and Quality Measurement: Intercom developed a telemetry infrastructure using Honeycomb to track AI skill usage and ensure consistent quality across hundreds of engineers.
  • Skills Repository and Automated Standards: A centralized repository of coding “skills” was built with hooks that enforce engineering best practices automatically, reducing manual oversight and errors.
  • Agent-First Workflow: The company redesigned technical workflows around AI agents, incorporating CLIs, multi-channel platforms (MCPs), and ephemeral APIs to prepare for AI-driven product experiences.
  • Permission and Accountability Framework: This framework facilitated rapid and secure AI adoption by defining clear responsibility boundaries.

Impact on Engineering Culture and Product Development

With backlog zero becoming achievable, Intercom fostered a more agile and responsive engineering culture. Their investment in AI was treated as a strategic asset, with costs balanced against productivity gains. The internal AI experience directly informed customer-facing product decisions, enabling the creation of agent-friendly SaaS offerings that reduce user friction and improve conversion rates.