The New Bottleneck: What Breaks When AI Ships Faster Than Your Team
About this session
Six months ago, our engineering team went all in on agents. Claude Code, Cursor, custom skills, agent-first architecture. Feature cycle time dropped 99%. PR throughput went 4 to 5 times higher. In production, sustained over a full quarter.
What we didn't expect: the bottleneck moved. Past testing. Past development. Past design. All the way upstream to product and UX. Our agents could build features faster than our team could define them.
This talk is about what breaks when engineering velocity outruns the rest of your organization. The architecture patterns that hold up under agent-first development. The rituals and roles that stop working. The new metrics that matter. And the honest playbook for redesigning the SDLC when your constraint has moved somewhere new.
No theater. Real production numbers. What to try Monday.
Speaker
Key takeaways
- 1. The architectural patterns that scale under agent-first development: harness engineering, context architecture, and the primitives every team needs before going all in.
- 2. Which engineering rituals stop working when cycle time collapses, and what to replace them with so the team doesn't drown in coordination overhead.
- 3. Where the constraint actually moves when agents handle the build, and how to redesign upstream product and design workflows so engineering doesn't sit idle.