Pistes
Platform operations
Routing models, cost controls, telemetry, release governance, and incident response patterns.
Blog
5 notes de mise en œuvre dans cette piste.
AI runtime incident triage patterns
Runtime incidents need triage paths that distinguish provider outage, quality regression, policy breach, tool failure, and cost runaway.
9 lecture min.
Provider fallback drills for model operations
Fallback policies only work when teams rehearse provider degradation, quality regressions, cost spikes, and shutdown decisions.
8 lecture min.
Release gates for prompt and model changes
Treat prompt and model updates like code changes with explicit approvals.
7 lecture min.
Observability signals that matter for AI systems
Focus on decision quality and escalation behavior, not token counts alone.
9 lecture min.
Model routing policies for cost and latency control
Route tasks by complexity and risk to balance quality, latency, and budget.
8 lecture min.
Base de connaissances
4 références dans cette piste.
AI incident postmortem structure
A postmortem structure tailored for model and workflow incidents.
Platform operationsModel routing policy template
Define model selection policy by task complexity and risk class.
Platform operationsProvider fallback drill plan
Drill plan for testing provider fallback, degraded mode, cached-answer behavior, and shutdown decisions.
Platform operationsRuntime incident triage checklist
Checklist for classifying AI runtime incidents by failing layer, impact, fallback state, owner, and customer exposure.