Roadmap

Free

AI Agents Engineer

Go from Python developer to production AI Agent Engineer by building real autonomous systems: master the agent loop, tool use, memory, planning, multi-agent orchestration, agentic RAG, evaluation, safety, and deployment with LangGraph, MCP, and modern agent frameworks. Assumes LLM basics; focuses end-to-end on shipping agents that work in the real world.

Intermediate

12 weeks36 topics · ~18h

Curriculum

Your step-by-step plan

Watch curated videos

// Modules

Module 1

Foundations of Agentic AI

0/4 topics · 0%

Start

Module 2

Tool Use & Structured Output

0/3 topics · 0%

Start

Module 3

Agent Cognition: Memory, Planning & Reflection

0/4 topics · 0%

Start

Module 4

Building Agents with LangGraph

0/3 topics · 0%

Start

Module 5

Multi-Agent Systems

0/3 topics · 0%

Start

Module 6

Agent Frameworks & MCP

0/4 topics · 0%

Start

Module 7

Agentic RAG

0/3 topics · 0%

Start

Module 8

Evaluation, Observability & Human-in-the-Loop

0/3 topics · 0%

Start

Module 9

Agent Safety & Security

0/3 topics · 0%

Start

Module 10

Deploying Agents to Production

0/3 topics · 0%

Start

Module 11

Capstone & Career

0/3 topics · 0%

Start

Start this roadmap free

Small daily execution creates big career change. Sign up free and track every topic you complete.

AI Agents Engineer

Your step-by-step plan

Foundations of Agentic AI

Tool Use & Structured Output

Agent Cognition: Memory, Planning & Reflection

Building Agents with LangGraph

Multi-Agent Systems

Agent Frameworks & MCP

Agentic RAG

Evaluation, Observability & Human-in-the-Loop

Agent Safety & Security

Deploying Agents to Production

Capstone & Career

Foundations of Agentic AI

What Are AI Agents? Agents vs Workflows vs Chatbots

The Agent Loop: ReAct and Plan-Act-Observe

Anatomy of an Agent: Model, Tools, Memory, Control Loop

Build Your First Agent From Scratch (No Framework)

Tool Use & Structured Output

Function & Tool Calling Fundamentals

Structured Output & Validation with Pydantic

Building a Robust Multi-Tool Agent

Agent Cognition: Memory, Planning & Reflection

Short-Term Memory & Context Window Management

Long-Term & Vector Memory

Planning & Task Decomposition

Reflection & Self-Correction (Reflexion)

Building Agents with LangGraph

LangGraph Fundamentals: State, Nodes & Edges

Building a Stateful ReAct Agent with Checkpointing

Streaming & Persistence in LangGraph

Multi-Agent Systems

Multi-Agent Architectures & the Supervisor Pattern

Agent Handoffs & Swarm Collaboration

Agent Debate & Critic Patterns

Agent Frameworks & MCP

The Agent Framework Landscape

Building a Crew with CrewAI

Model Context Protocol (MCP) Fundamentals

Build & Connect Your Own MCP Server

Agentic RAG

From RAG to Agentic RAG

Building an Agentic RAG System (Retrieval as a Tool)

Corrective & Self-RAG (Adaptive Retrieval)

Evaluation, Observability & Human-in-the-Loop

Tracing & Observability for Agents

Evaluating Agents: Trajectory Eval & LLM-as-Judge

Human-in-the-Loop & Approval Workflows

Agent Safety & Security

Prompt Injection & Agent Security

Tool Sandboxing & Permission Boundaries

Guardrails, Cost & Loop Control

Deploying Agents to Production

Serving an Agent as an API (FastAPI)

Streaming Agent Responses

State Persistence & Scaling Agents in Production

Capstone & Career

Capstone: Build & Ship a Production Agent

Building Your AI Agent Portfolio

AI Agent Engineer Interview Prep

Start this roadmap free