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 in Operations
- Transitioning from static runbooks to reasoning agents: The evolution of IT automation
- Anatomy of an agent: Reasoning loops, tool usage, memory, and planning
- Determining when to automate versus when to retain human involvement
Agent Frameworks and Architectures
- Single-agent patterns: ReAct, Plan-and-Execute, and tool-calling loops
- Multi-agent architectures: Supervisor, hierarchical, and swarm models
- Framework comparison: LangGraph, CrewAI, AutoGen, and custom implementations
- Creating your first operational agent: Querying monitoring, diagnosing issues, and proposing solutions
Tool Integration for IT Operations
- Connecting agents to Prometheus, Grafana, Datadog, and PagerDuty APIs
- Agent-based log querying: Integration with Elasticsearch, Loki, and Splunk
- Leveraging infrastructure tools: kubectl, Terraform, and Ansible via agent actions
- Designing secure tool interfaces with parameter validation and idempotency
Automated Incident Response
- Automated incident triage: Severity classification and routing
- Generating root cause hypotheses and collecting evidence
- Automated remediation: Executing 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
- Approval gates and escalation policies for critical operations
- Guardrail strategies: Action allowlists, blast radius limits, and rollback guarantees
- Audit trails and decision provenance for compliance purposes
Multi-Agent Orchestration for Complex Incidents
- Coordinating specialist agents: Triage, diagnosis, and remediation agents
- Inter-agent communication and shared context management
- Resolving conflicts when agents suggest contradictory actions
- End-to-end major incident simulation featuring multi-agent responses
Observability and Evaluation
- Tracing agent reasoning chains for debugging and auditing
- Assessing agent decision quality: Precision, recall, and time-to-resolution
- Feedback loops: Learning from operator overrides and final 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
- Managing agent failures: Protocols for when the agent itself malfunctions
- Building the business case and measuring ROI for autonomous operations
Requirements
- Practical experience in IT operations, DevOps, or SRE practices.
- Proficiency in Python scripting and REST APIs.
- Foundational knowledge of LLM capabilities and prompt engineering.
Audience
- SRE and DevOps engineers investigating AI-driven automation.
- Platform engineers developing self-healing infrastructure.
- IT operations leaders evaluating agentic AI for incident management.
14 Hours
