All tracks
Intermediate~13 hours13 lessons

Agentic AI Engineer

Design reliable AI agents with tools, memory, planning, guardrails, and human review workflows. Learn the patterns used in production agentic systems, not just demos.

What you'll learn

Tool calling and function design
Agent loop architecture
Planner-executor-verifier pattern
LangGraph-style state machines
Agent memory: episodic, semantic, procedural
Human approval gates and HITL
Tool validation and schema enforcement
Agent rollback and recovery
MCP integration and server development
Agent observability and tracing
Agent evaluation frameworks
Multi-agent failure modes
Agentic AI capstone project

Learning outcomes

1Build a reliable tool-calling agent with structured outputs
2Implement planning patterns that reduce failure loops
3Design human-in-the-loop workflows for high-stakes actions
4Trace, debug, and evaluate agent behavior in production
5Integrate MCP servers into agentic applications

Related lessons

Browse all lessons

Up next after this track

Advanced
12h

LLMOps and AI Observability

Operate AI systems with tracing, evaluation pipelines, regression tests, cost monitoring, and production dashboards. Learn the engineering discipline behind reliable LLM products.

12 lessons

Prompt versioning and experiment trackingDataset versioning for evaluationEvaluation pipelines: automated and humanLLM-as-judge patterns and calibration+8 more
Preview track
Advanced
11h

AI System Design Interview

Prepare for senior AI engineering interviews with system design walkthroughs, architectural tradeoffs, metric definitions, failure mode analysis, and mock interview practice.

11 lessons

RAG system design end to endAI chatbot system designAgent platform architectureLLM gateway and routing design+7 more
Preview track

Weekly newsletter

Get practical AI engineering insights in your inbox.

Weekly guides, interview prep, architecture breakdowns, and production lessons for engineers building with AI — free forever.

Subscribe free