🧭 Course · 14 lessons · about 8.3 hours
Agentic AI & Automation
Design agents that plan, call tools, keep state, and work with humans in the loop, then test, trace, and secure them for production.
Start lesson 1 →Roles: Agentic AI Engineer · AI Automation Engineer
Before you start
Part of these career paths
Module 1 · Agent Foundations
What makes a system an agent, and how it remembers.
- Lesson 0130 minWhat Is an AI Agent? The Plan–Act–Observe LoopWorkflows versus agents, the reasoning-and-acting loop, when an agent is the wrong tool, and building a minimal agent from scratch.
- Lesson 0230 minAgent State and MemoryModel agent state explicitly, manage short-term context, add long-term memory with retrieval, and avoid memory that leaks or drifts.
- Lesson 0330 minPlanning, Reflection and Error RecoveryPlan-and-execute, self-critique, retries, and fallbacks: patterns that make multi-step agents finish tasks reliably.
Module 2 · Orchestration
Build agent workflows as graphs, connect tools with MCP, and coordinate several agents.
- Lesson 0440 minBuilding Agent Workflows with LangGraphModel an agent as a graph of nodes and edges with typed state, conditional routing, checkpoints, and resumable runs.
- Lesson 0530 minHuman-in-the-Loop Approvals and InterruptsPause an agent before risky actions, collect approval or edits from a person, and resume safely with an audit trail.
- Lesson 0635 minModel Context Protocol (MCP) — Connecting Agents to Tools and DataHow MCP clients and servers work, building a small MCP server in Python, and the security model for exposing tools.
- Lesson 0735 minMulti-Agent Systems — Supervisors and HandoffsSupervisor, router, and handoff patterns; when several agents beat one; and how to keep their cost and behaviour under control.
- Lesson 0835 minAgent Frameworks Compared — LangGraph, OpenAI Agents SDK and CrewAIBuild the same small agent three ways and compare control, state, tracing, lock-in and production readiness to choose a framework.
- Lesson 0935 minBrowser and Computer-Use AgentsHow agents drive browsers and desktops, when to use Playwright tools instead, and how to keep these agents reliable and safe.
Module 3 · Production Agents
Prove agents work, see what they do, and limit what they can break.
- Lesson 1035 minTesting, Evaluating and Tracing AgentsTrajectory and outcome evaluation, scenario test suites, tracing every step, and the production metrics that matter for agents.
- Lesson 1135 minSecuring Agents — Tool Permissions and Abuse CasesLeast-privilege tools, sandboxing, indirect prompt injection through tool results, spending limits, and abuse-case testing.
- Lesson 1235 minDeploying Long-Running Agents — Queues, Checkpoints and Cost LimitsRun agents as background jobs with queues, durable checkpoints, timeouts, budgets and resumable runs, and monitor them in production.
- Lesson 1350 minCapstone — A Tool-Using Support AgentPlan and build a support agent that searches a knowledge base, calls tools, asks for approval on refunds, and is traced and evaluated.
- Lesson 1445 minAgentic AI Interview PrepAgent architecture, tool design, memory, evaluation and security questions from agentic AI interviews, with model answers and design exercises.
