ModulesSAI-260
SAI-260 table of contents
Observability, Reliability, and FinOps
Measure workload health, behavior, evaluation quality, capacity, cost, incidents, and operational evidence.
Learning outcomes
What you should be able to do
- Define useful AI service indicators
- Connect evaluation signals to operations
- Measure capacity, unit cost, and accepted outcomes
Curriculum
Work through 5 sections in order.
The chapters are individually addressable documentation pages. You can link directly to a concept from another program, architecture decision, or implementation guide.
Operations foundations
Define operational outcomes and the evidence required to explain them.
Introduction to AI operations
Operate AI as a measurable service whose technical health, behavior, risk, and cost can change independently.
Observability and operational evidence
Design signals that explain service health, AI behavior, policy outcomes, change, and incidents without leaking sensitive content.
Evidence by design
Design evidence alongside controls so important decisions, releases, configurations, and operating events can be verified.
Health and quality signals
Measure service health and AI behavior across the request lifecycle.
Reliability and response
Set service objectives and prepare for degradation, incidents, and recovery.
Service objectives, incidents, and recovery
Define meaningful objectives and operational responses for degraded, unsafe, or unavailable AI behavior.
Capacity, reliability, and recovery
Define capacity envelopes, degradation behavior, service objectives, recovery targets, and tested restoration evidence.
Capacity and economics
Connect demand, capacity, performance, cost, and accepted outcomes.
Capacity, cost, and unit economics
Measure constrained capacity, demand, waste, unit cost, and accepted outcomes without optimizing spend in isolation.
Controlled change and versioning
Version complete AI behavior, assess change impact, approve promotion, support rollback, and retire superseded assets.
Architecture decision records
Record context, options, control consequences, evidence, dependencies, limitations, and reversal triggers for material decisions.
Apply and assess
Create an operations package and verify the module outcomes.
Practical completion package
- AI service indicator and objective catalog
- Telemetry and AI-quality signal map
- Incident and recovery playbook
- Capacity and unit-economics model
- Operational evidence report
Current release boundary
This curriculum supplies an operating method, not universal SLO targets, cost forecasts, or a production monitoring configuration. Workload baselines, thresholds, retention, and tool-specific dashboards require measured local validation.