Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Agentic AI for Operations
- From static runbooks to reasoning agents: the evolution of IT automation
- Agent anatomy: reasoning loop, tool use, memory, and planning
- When to automate versus when to keep humans in the loop
Agent Frameworks and Architectures
- Single-agent patterns: ReAct, Plan-and-Execute, and tool-calling loops
- Multi-agent architectures: supervisor, hierarchical, and swarm patterns
- Framework comparison: LangGraph, CrewAI, AutoGen, and custom agents
- Building your first operational agent: querying monitoring, diagnosing, and proposing solutions
Tool Integration for IT Operations
- Connecting agents to Prometheus, Grafana, Datadog, and PagerDuty APIs
- Log querying with agents: integrating Elasticsearch, Loki, and Splunk
- Infrastructure tool use: kubectl, Terraform, and Ansible via agent actions
- Designing safe tool interfaces with parameter validation and idempotency
Incident Response Automation
- Automated incident triage: severity classification and routing
- Generating root cause hypotheses and gathering evidence
- Automated remediation: restart, scale, rollback, and failover actions
- Building an incident runbook agent with progressive autonomy levels
Safety, Guardrails, and Human-in-the-Loop
- Action classification: read-only, low-risk, high-risk, and destructive
- Approval gates and escalation policies for critical operations
- Guardrail patterns: action allowlists, blast radius limits, and rollback guarantees
- Audit trails and decision provenance for compliance
Multi-Agent Orchestration for Complex Incidents
- Coordinating specialist agents: triage, diagnosis, and remediation agents
- Inter-agent communication and shared context management
- Conflict resolution when agents propose contradictory actions
- End-to-end major incident simulation with multi-agent response
Observability and Evaluation
- Tracing agent reasoning chains for debugging and auditing
- Evaluating agent decision quality: precision, recall, and time-to-resolution
- Feedback loops: learning from operator overrides and outcomes
- Cost tracking and token economics for operational agents
Production Deployment and Operations
- Deploying agents as services: APIs, webhooks, and scheduled jobs
- Gradual autonomy rollout: moving from shadow mode to full auto-remediation
- Runbook for agent failures: procedures when the agent itself breaks
- Building the business case and measuring ROI for autonomous operations
Requirements
- Experience with IT operations, DevOps, or SRE practices.
- Familiarity with Python scripting and REST APIs.
- A basic understanding of LLM capabilities and prompt engineering.
Audience
- SRE and DevOps engineers exploring AI-driven automation.
- Platform engineers building self-healing infrastructure.
- IT operations leads evaluating agentic AI for incident management.
14 Hours
