Five runbooks for the five things that actually page you on an AI service, each with the first command, the branch, and what to do at each branch.
A runbook is a decision tree for somebody who was asleep four minutes ago. It is not documentation, not an architecture overview and not a list of possible causes: it is symptom, first command, what the output means, and what to do about each answer. Below are five, for the five alerts that actually fire on an AI service.
What a runbook is, and is not
The format that works has five parts, and pages that omit the third are the ones nobody uses.
Part
Description
Most runbooks are useless. Either they're too abstract ('check the logs') or they're a 40-page...
When production blinks, engineers reach for logs, metrics, and runbooks—not another generic chatbot....
The Runbook That Lied to Me at 3am The pager went off at 3:14am for a wedged OpenStack...
An operator runbook that maps stop signals to containment, evidence preservation, and recovery gates.
A practical look at building one AI desk that talks to your documents, your database, and the web....
Separate reusable support instructions from MCP-style capabilities, add deterministic routing and permission gates, and test the…
