How Building with AI Can Double the Throughput of Your Engineering Team
summary
Claimed result is concrete: 2x throughput in under a year. Platform choice is explicit: Claude Code onboarded to a 15‑year Rails monolith, given durable skills and hooks into prod. Measured outcomes are striking: PR throughput doubled, 17.6% auto‑approved with SOC 2 signoff and the CI collapsed under volume. A real skill actually investigates leaked Snowflake metadata, runs analysis and returns next steps in two minutes, showing the approach works end to end.
AI-written summary · about
chapters (11)
- 0:00Intercom's AI transition
- 1:24Scaling AI for customers
- 2:39Engineering productivity goals
- 3:24Project 2X and AI adoption
- 5:51Leadership for AI transformation
- 7:21Platform and tool strategy
- 9:52Agent-first engineering
- 10:51Core engineering principles
- 14:35Measuring maturity and growth
- 16:12Data-driven improvements
- 19:11Practical skills and future
related talks
44mSpeed Is Easy, Trust Is Hard: AI's Real Impact on Developer Productivity
42m10x Engineering: How GenAI Tools Transformed My Team's Productivity
23mThe AI productivity paradox: Why feeling faster isn't the same as going faster
17mAI-Driven Platform Engineering
27mEngineering in the Age of AI: Making AI Work for Us, Not Replace Us
26mYour pipeline is the bottleneck
45m"How AI improved our performance by 20%" and other bedtime stories
18mDispatch from the Future: building an AI-native Company