Expedia Group reimagines platform engineering to serve AI agents alongside humans
Expedia Group's platform was designed for human engineers — microservices, SDKs, and UIs optimized for human ergonomics — and was not ready to support agents as a distinct user group. Proprietary abstractions on top of standard tech made the platform unfamiliar to agents trained on the open ecosystem.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Agent receives platform task
Engineers ask agents like Claude to perform platform operations such as watching a CI/CD pipeline.
Expedia Group began shipping agent-native infrastructure including the Tarmac CLI (covering CI/CD, Kubernetes, and log exploration), MCP servers with a capability registry, markdown-based agent skills packaging tribal knowledge, and the Koda internal app platform. A 'no-coding-allowed' Ralphathon hackathon confirmed the hypothesis that structured experimentation — not just instruction — is required to shift engineer workflows.
What failed first
When asked to perform platform tasks without proper agent interfaces, agents routed around the platform by logging into web UIs through browser automation — inspecting cookies and session state — producing brittle, unreliable operations that the platform team explicitly wanted to avoid.
Results
Cost replacedagents spend less time fumbling around and more time doing useful work. And the cost profile of that work improves