GenAI Engineer PathFrom zero to agentic AI
4

AI Agents

Move from single calls to systems that decide and act. Learn what makes something an agent, how tools and memory work, the difference between autonomous and workflow agents, human oversight, and the Model Context Protocol.

What you will be able to do

  • Tell agents apart from fixed workflows and pick the right one
  • Give an agent tools and short- and long-term memory
  • Design workflow agents with orchestration and checkpoints
  • Add human-in-the-loop control and connect tools via MCP
0 of 7 topics complete0%

  1. Agent Basics

    Beginner

    What separates an agent from a workflow: an LLM that chooses its own steps and tools in a loop. Start with the most cited, practical framing of the space.

    40 min3 resources · 1 video

  2. Tools & Function Calling

    Intermediate

    Tools are how an agent affects the world: calling APIs, querying databases, running code. Learn how function calling lets a model request actions reliably.

    40 min3 resources · 1 video

  3. Memory Management

    Intermediate

    Agents need state. Learn the split between short-term (conversation) and long-term (persistent) memory and the patterns for storing and recalling it.

    35 min2 resources · 1 video

  4. Autonomous Agents

    Advanced

    Fully autonomous agents plan, act, observe, and re-plan with minimal human input. Understand the canonical architecture and its real-world limits.

    45 min3 resources · 1 video

  5. Workflow Agents

    Advanced

    Most production agents are structured workflows, not free-running loops. Learn orchestration patterns, checkpointers for durable state, and when to constrain the agent.

    1 hr3 resources · 1 video

  6. Human-in-the-Loop (HITL)

    Intermediate

    For consequential actions, an agent should pause for human review. Learn the patterns for approvals, interrupts, and editing agent state mid-run.

    30 min2 resources · 1 video

  7. Model Context Protocol (MCP)

    Intermediate

    MCP is an open standard for connecting agents to tools and data sources, the USB-C of AI integrations. Learn it from the official docs and a clear introduction.

    1 hr3 resources · 1 video

Put it to work

Apply what you learned by building real projects.

Test your thinking

Challenge yourself with scenario-based questions. Need 80% to mark complete.