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

Overview

Shownote

Highlights

Transcript

Chapters

Pins

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

How I AI

4 DAYS AGO
How I AI

How I AI

4 DAYS AGO
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

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,...

Highlights

This episode features Brian Scanlan, Senior Principal Engineer at Intercom, discussing how the company achieved a dramatic acceleration in engineering velocity and quality by embedding AI deeply into its development culture and infrastructure.
00:00
AI doubles engineering throughput at Intercom in nine months
02:41
Intercom has met the moment in product and team transformation with AI
05:01
Engineers using Claude Code during PTO return more skilled, suggesting companies should increase PTO and parental leave
07:03
The engineering team has twice the throughput compared to nine months ago
12:51
All technical work will become agent-first
14:28
Intercom is currently focused on using Opus for everything and treating it as an investment, delaying cost optimization until they've reaped significant benefits
19:27
AI magnifies both strengths and weaknesses
21:22
Intercom built an LLM judge to evaluate pull request description quality after Claude Code produced poor outputs
24:03
Enforcing high-quality PR descriptions via Git hooks increased engineering competence
29:37
It's great when robots can do work as well as the best engineers
30:16
Basic usage info is sent to Honeycomb via a shared key to support internal skill discovery
32:10
Intercom built a tool to provide personalized feedback on users' Claude Code usage compared to others in the organization
36:09
Upload Claude Code session JSON files to S3 for anonymization and internal evaluation
39:20
Core plugins have safety hooks and require rigorous evaluation and testing
44:50
The skill achieves 100x capability through feedback loops and cross-repo reliability
46:45
Re-implementing a Go microservice in Ruby was accomplished in a single Claude Code session
52:31
Lobster emojis and live broadcast serve as a growth hack
53:32
SaaS products must be agent-friendly, supporting CLIs, MCPs, and ephemeral APIs for autonomous agent decision-making
1:01:55
Products don't need to be perfect for agents—they need navigable CLIs and APIs
1:03:49
Escape button usage reveals critical conversion drop-off points
1:11:00
All work will be agent-first in the near future

Chapters

Introduction to Brian Scanlan
00:00
Why Intercom went all-in on AI for both product and engineering
02:40
The breakthrough moment with Opus 4.6 and Christmas break 2025
05:01
Demo: Intercom’s merged PRs per R&D head
07:02
Agent-first work as a fundamental reimagining of technical workflows
12:50
The cost tradeoff: treating AI spend as an investment
14:27
Measuring quality
16:47
Demo: Shipping a redirect in the Rails monolith with Claude Code
21:22
Creating a custom PR skill
24:03
Building a software factory with predictable quality standards
26:33
Telemetry infrastructure: Honeycomb for skill usage tracking
30:15
Session data collection and personalized usage insights
32:10
Quick overview
36:08
Walking through Intercom’s skills repository
39:20
Deep dive: The flaky spec skill and how it reached 100x capability
42:16
The “and then” workflow for building comprehensive skills
46:44
The live website and overview of workflows
52:31
How internal AI experience informs customer product decisions
53:32
Making SaaS products agent-friendly with CLIs and helpful hints
56:18
Why conversion drop-off is invisible in agent-driven workflows
1:03:49
Lightning round and final thoughts
1:05:28

Transcript

Brian Scanlan: Suddenly, you started realizing that you have to think bigger about things, or that your imagination is now the barrier, not the tool. Claire Vo: How is this not happening in your organization? Like, literally, the physical limits of my abi...