Agentic AI Engineer Path
Build autonomous AI systems
Visual Roadmap
10 stages · click any stage to jump
LLM fundamentals
The model behaviour agents depend on: co…
Tool Calling
Function calling, schemas and safe execu…
Agent Loops
Reason-act loops, stopping conditions an…
Memory & Planning
Short- and long-term memory, task decomp…
Workflows
Graph-based orchestration, background jo…
Multi-Agent Systems
Coordination, delegation and when one ag…
MCP
Model Context Protocol: one tool server,…
Agent Evaluation
Outcome and step-by-step evaluation of a…
Always-On Agents
Agents with their own computer, schedule…
Production Agents
Observability, security and cost control…
Overview
Master agentic AI: tool calling, agent loops, state and memory, planning, multi-agent orchestration, MCP, and production agent systems with evaluation and security.
Learning outcomes
- Design and build production AI agents
- Implement agent loops with tool calling and memory
- Orchestrate multi-agent systems and workflow graphs
- Apply MCP for tool ecosystems
- Evaluate, secure and observe production agents
Stages
The model behaviour agents depend on: context, sampling and structured output.
Short- and long-term memory, task decomposition and replanning.
Building AI AgentsCoordination, delegation and when one agent is better than many.
Agentic WorkflowsOutcome and step-by-step evaluation of agent runs.
Agents with their own computer, schedule, identity and approval rules.
Observability, security and cost control for agents in production.