AI Operations

Writing filed under AI Operations.

AI incident reviews need model context

An AI incident review has to include prompt, model, retrieved context, tool calls, and approval state.

April 22 20266 min read

#incident review #ai ops #models

Agent observability needs user-level events

AI operations need logs that explain what the agent did in product terms, not only infrastructure terms.

August 7 20256 min read

#agents #observability #ai ops

Kubernetes 1.30 was an upgrade planning reminder

Kubernetes releases are a calendar discipline that reaches beyond cluster administration.

April 24 20246 min read

#kubernetes #operations #upgrades

OpenTelemetry profiling brought performance closer to the main stack

Profiling moving into the OpenTelemetry conversation made performance feel closer to traces, metrics, and logs.

March 27 20246 min read

#opentelemetry #profiling #observability