By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
How I AIHow Intercom 2X'd engineering velocity with Claude Code | Brian Scanlan
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
At a glance
WHAT IT’S REALLY ABOUT
Intercom doubles engineering throughput by going all-in on Claude Code
- Intercom committed company-wide to AI adoption in engineering after model capability inflections made agents feel “transformative,” then standardized on Claude Code to scale usage.
- They measure “merged PRs per R&D head” as a leading indicator of adoption and report roughly 2× throughput in nine months, with bottlenecks shifting from CI to code review.
- Intercom treats AI token spend as an investment phase (optimizing later) while building a software-factory approach with predictable standards enforced via skills and hooks.
- They built telemetry pipelines (Honeycomb, Snowflake, S3 session logs) to understand tool usage, coach individuals, and continuously improve skills rather than “flying blind.”
- Intercom claims quality has not degraded—citing faster idea-to-shipping times, no incident spike, and external research (Stanford) suggesting code quality trends upward.
IDEAS WORTH REMEMBERING
5 ideasModel inflections change the constraint from tooling to imagination.
Scanlan describes a shift where engineers spend less time coaxing tools and more time delegating outcomes, enabling bigger bets and faster iteration when models reached a new capability tier.
Treat internal developer tooling like a product—with metrics, telemetry, and iteration loops.
Intercom instruments skills and sessions, mines usage data, and builds dashboards so they can debug adoption, improve workflows, and deliver “enablement” rather than just handing out an API key.
A simple throughput metric can drive adoption—if paired with high trust and quality guardrails.
They use merged PRs per R&D head as a crude but motivating leading indicator, while explicitly rejecting “quality slop” via standards, reviews, and targeted quality measures.
Enforce process quality upstream using skills and hooks, not wikis.
Intercom created a “Create PR” skill because AI-generated PR descriptions degraded; they blocked default PR creation paths and required the skill, raising PR-description quality per an internal LLM judge.
Agent-first work shifts bottlenecks—fix the new choke points.
As AI increased output, CI became overloaded and had to be optimized; after that, code review became the bottleneck, implying organizations must continuously rebalance systems around higher throughput.
WORDS WORTH SAVING
5 quotesYou have to think bigger about things, or that your imagination is now the barrier, not the tool.
— Brian Scanlan
Today we are seeing twice the number of throughput as we did compared to nine months ago on our engineering team. Now it's like, why can't it be 10X?
— Brian Scanlan
We are treating it as, like, an investment at this point… everyone just turn on Opus for everything… and care about the bill later.
— Brian Scanlan
Backlog zero is a realistic thing for teams to be able to go after.
— Brian Scanlan
Your conversion rate drop-off point is somebody pressing the escape button.
— Claire Vo
SPEAKERS
Brian Scanlan
guestSenior principal engineer at Intercom focused on AI-assisted engineering workflows and developer velocity.
Claire Vo
hostProduct leader and host of the How I AI podcast.
High quality AI-generated summary created from speaker-labeled transcript.
