About

Agent-native operations — incident and customer comms

Both were built around a human doing the first read — getting paged or assigned, gathering context, deciding, acting. When an agent takes that pass instead, the workflow around it is worth redesigning rather than retrofitting. These posts work through how: the design choices and trade-offs, one piece at a time.

Most of the posts sit in on-call and incident response: the agent design behind it — MCP servers, prompt and context engineering, the security boundaries around LLMs — the observability tooling it leans on, and the customer-facing communication that happens while something is broken.