The AI-Native Engineering Playbook

This playbook is about how software engineering and R&D teams are redesigning their practices to build and ship software with agentic AI. As agents take on more of the coding itself, the work shifts to everything around it: finding where delivery actually slows, deciding what people and agents each do best, making the codebase safe for agents to work in, verifying what they produce before it ships, and growing the engineers who now direct them.

Every practice here is grounded in what engineering leaders at GitLab and across our customer community are actually doing, and these pages will keep changing as the practice does, so treat them as a current, shared reference rather than a finished manual.