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
- Transitioning from static runbooks to reasoning agents: the evolution of IT automation
- Agent anatomy: reasoning loops, tool usage, memory, and planning
- Determining when to automate versus when to retain human oversight
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
- Creating 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: Elasticsearch, Loki, and Splunk integration
- Infrastructure tool usage: kubectl, Terraform, and Ansible via agent actions
- Designing secure 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
- Developing 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
- Establishing approval gates and escalation policies for critical operations
- Guardrail patterns: action allowlists, blast radius limits, and rollback guarantees
- Implementing audit trails and decision provenance for compliance
Multi-Agent Orchestration for Complex Incidents
- Coordinating specialist agents: triage, diagnosis, and remediation agents
- Managing inter-agent communication and shared context
- Resolving conflicts when agents propose contradictory actions
- Conducting end-to-end major incident simulations with multi-agent responses
Observability and Evaluation
- Tracing agent reasoning chains for debugging and auditing
- Evaluating agent decision quality: precision, recall, and time-to-resolution
- Implementing feedback loops: learning from operator overrides and outcomes
- Tracking costs and token economics for operational agents
Production Deployment and Operations
- Deploying agents as services: APIs, webhooks, and scheduled jobs
- Rolling out gradual autonomy: from shadow mode to full auto-remediation
- Creating runbooks for agent failures: managing scenarios where the agent itself breaks
- Building the business case and measuring ROI for autonomous operations
Requirements
- Practical experience with IT operations, DevOps, or SRE practices.
- Familiarity with Python scripting and REST APIs.
- A foundational 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
