Observed Signal · Apr 20, 2026 · Case Study · Source: Lennys Newsletter · Impact: 2/5 · Sentiment: Positive
Intercom Doubles Engineering Velocity Using Claude Code
Brian Scanlan, senior principal engineer at Intercom, describes how the company adopted an AI-first engineering approach and used Claude Code to double merged PRs per R&D employee in nine months while maintaining code quality. Intercom rolled out Claude Code broadly—100% of engineers plus designers, PMs and TPMs ship code via the tool—and built telemetry (using Honeycomb) to measure AI adoption and quality. They created a skills repository that enforces engineering standards, implemented permission and accountability frameworks, and prepared their product and infrastructure for an agent-first future with CLIs, Model Context Protocol (MCP) servers, and ephemeral APIs. The interview includes demos, a deep dive on flaky-spec automation, and discussion of treating AI spend as an investment and achieving 'backlog zero.'
Practical, operational case study showing that integrated LLM tooling and governance can materially raise engineering throughput and quality; useful reference for enterprises adopting AI-first development but not a platform-level policy or major vendor announcement.
Track Intercom Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Intercom doubled merged PRs per R&D employee within nine months using Claude Code.
- 100% of Intercom engineers, plus designers, PMs, and TPMs, are shipping code via Claude Code.
- Intercom built telemetry infrastructure (using Honeycomb) to track AI adoption and quality across hundreds of engineers.
- Intercom created a skills repository with automated hooks to enforce engineering standards and a permission/accountability framework for AI usage.
- Intercom is preparing for agent-first workflows by adding CLIs, Model Context Protocol (MCP) servers, and ephemeral APIs.
Connected Companies & Entities
5 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Intercom Doubled Engineering Velocity with Claude Code
Brian Scanlan, Senior Principal Engineer at Intercom, describes how Intercom doubled merged pull requests per R&D employee in nine months by adopting Claude Code with custom skills, telemetry, and a permissive culture. Intercom instruments skill usage in Honeycomb, stores anonymized Claude Code sessions in S3, and built dashboards to surface adoption and performance. The company emphasized that mature CI/CD, test coverage, and a high-trust culture were prerequisites; AI amplified existing strengths. Intercom enforces quality via custom skills (e.g., a “Create PR” skill that constrains GitHub CLI use and requires context-rich PR descriptions) and reports improving code-quality metrics in partnership with Stanford researchers. Scanlan argues leadership must give permission and take accountability for experimentation, and advocates designing agent-friendly product APIs and CLIs to avoid customers building fragile agent integrations themselves.
Using Claude Code in Full‑Stack Development Workflow
An individual full‑stack engineer describes five months of daily use of Claude Code (alongside Gemini AI and GitHub Copilot) to accelerate full‑stack SaaS development. The author reports building six production applications with an 87% implementation acceleration, ~80%+ test coverage, and no critical production issues from AI‑generated code after human review. The post outlines a four‑phase workflow (architecture & design; server‑side implementation; frontend implementation; testing & security), lists high‑ROI tasks for the AI (boilerplate, error handling, database optimization, security review, documentation), and describes areas where the agent struggles (business logic, custom integrations, performance profiling, architectural trade‑offs). The author emphasizes mandatory human review, testing, staging, canary rollouts, and feature flags before production deployment.
Engineer Uses Claude Code to Query Entire Codebase
Al Chen, a field engineer at Galileo (an observability platform for AI applications), built a system using Claude Code to query Galileo’s 15 separate repositories and combine that code context with Confluence documentation and Slack to answer complex, customer-specific technical questions. The implementation uses Model Context Protocols (MCPs) to join repo data with documentation and chat, includes a short script that pulls the latest main branch across repositories, and powers a “customer quirks” layer that generates hyper-personalized deployment guidance. The workflow is presented as a way to reduce engineering interruptions by enabling customer-facing teams to query the codebase directly and to scale single-customer knowledge into repeatable team processes. Tools mentioned include Claude Code, VS Code, Pylon, Confluence, Slack, Kubernetes, Intercom, Orkes and Tines.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.