Cambridge
Academy
In London

Introduction

AI-enabled cloud operations (AIOps) uses machine learning and automation to detect anomalies, correlate events, reduce alert noise, accelerate incident response, and improve reliability at scale. This practical program equips cloud operations leaders with modern approaches to observability, automated incident workflows, and governance—helping teams improve uptime, reduce MTTR, and operate cloud platforms efficiently and safely.

Course Objectives

By the end of this course, participants will be able to:

·        Understand AIOps concepts and where AI delivers value in cloud operations

·        Design an observability strategy across logs, metrics, traces, and events

·        Apply AI techniques for anomaly detection, event correlation, and alert optimization

·        Build automated incident response workflows and runbooks with human-in-the-loop controls

·        Integrate AIOps with ITSM/SRE practices to improve reliability and service quality

·        Establish governance, metrics, and an implementation roadmap for AI-enabled operations

Target Audience

This course is designed for:

·        Cloud operations managers, SRE leads, and platform operations leaders

·        NOC/SOC and incident management leaders working in cloud environments

·        DevOps and platform engineering managers

·        IT service management (ITSM) leaders responsible for incident/problem/change

·        Observability, monitoring, and reliability engineers

Course Outlines

Day 1: AIOps Foundations & Cloud Ops Readiness

·        Cloud operations challenges: scale, complexity, distributed systems, and noise

·        AIOps overview: anomaly detection, correlation, prediction, and automation

·        SRE/ITSM alignment: reliability targets, incident lifecycle, and operational rhythms

·        Data readiness: telemetry quality, tagging standards, and CMDB/service maps concepts

·        Activity: AIOps readiness assessment (tooling, data, process maturity, and gaps)

Day 2: Observability Strategy & Service Health Modeling

·        Observability pillars: logs, metrics, traces, events—what each is used for

·        Service health models: SLIs/SLOs, error budgets, and critical user journeys

·        Instrumentation strategy: standards, tagging, and context propagation concepts

·        Building service maps and dependency visibility for faster diagnosis

·        Workshop: Design an observability blueprint (service map + SLI/SLO set + telemetry plan)

Day 3: AI for Detection, Correlation & Alert Optimization

·        Anomaly detection concepts: baselines, seasonality, and threshold tuning

·        Event correlation: clustering alerts, reducing duplicates, and identifying root signals

·        Noise reduction: alert hygiene, suppression rules, and routing based on impact

·        Predictive insights: capacity risk signals and degradation forecasting concepts

·        Practical activity: Build an alert optimization plan + correlation rules for a case scenario

Day 4: Automated Incident Response & Runbook Orchestration

·        Incident response modernization: triage automation, suggested actions, and escalation

·        Runbooks and automation: triggers, approvals, and rollback safeguards

·        Human-in-the-loop design: when automation acts vs. recommends

·        Problem management integration: turning incidents into root-cause prevention actions

·        Case study: Incident simulation (major outage) using automated triage and runbook workflow

Day 5: Governance, Metrics & AIOps Implementation Roadmap

·        AIOps governance: roles, decision rights, approvals, and change control for automations

·        Controls and risk management: false positives, automation errors, and audit trails

·        Success metrics: MTTR, MTTD, alert volume, availability, SLO compliance, toil reduction

·        Adoption plan: pilot selection, training, operating rhythm, and continuous improvement