46:30

Abby Bangser opens with a clear-eyed status report on platform engineering: the concept of centralizing shared capabilities with self-service delivery is well understood, but the execution keeps going wrong in the same way. Organizations move from DevOps to platform engineering, but their platform teams end up becoming the new bottleneck — a centralized group drowning under the weight of the entire organization's requests, which is exactly what DevOps was supposed to fix. Abby traces this to an architectural problem: too many platforms are still built as centralized Terraform machines rather than as a marketplace of composable offerings, and too many platform engineers are wearing both the infrastructure-as-code hat and the product-experience hat simultaneously — which, at scale, guarantees a leaky abstraction and a frustrated user base. Her "platform as a product" test is blunt and useful: has the team ever said "no" to a feature request, or deprecated something? If not, they don't have a product — they have a request queue. The AI dimension is where the conversation gets most urgent. Abby's position is direct: AI agents are the new forcing function for platform maturity. The biggest misconception she wants to dismantle is the persistent equation of platform engineering with infrastructure-as-code: renaming your Terraform team doesn't count. Platform engineering is about building an experience — for human developers and increasingly for AI agents — that is self-service, compliant, and coherent at organizational scale. The Team Topologies model of interaction modes (from high-collaboration to fully automated on-demand APIs) gives a useful health check for where a platform actually sits on that maturity curve.