Udemy - Agentic AI Engineering - Multi-Agent Systems Mastery
Agentic AI Engineering: Multi-Agent Systems Mastery
https://WebToolTip.com
Published 8/2026
Created by Ganesh Ravikumar
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 67 Lectures ( 18h 12m ) | Size: 2.9 GB
Build production agents with LangGraph, CrewAI, AutoGen, tool use, memory, MCP & human-in-the-loop
What you'll learn
⚡ Explain agentic AI as a goal-driven loop with tools, state, and control — not a single chat reply
⚡ Build a pure-Python agent loop with tool schemas, structured outputs, and recovery from bad results
⚡ Design short-term and long-term memory and state schemas that survive production changes
⚡ Apply plan-execute-replan, reflection, and human-in-the-loop checkpoints with cost-aware limits
⚡ Build stateful LangGraph workflows with routers, checkpoints, streaming, and HITL breakpoints
⚡ Choose single-agent vs multi-agent designs and implement supervisor, sequential, and handoff patterns
⚡ Build multi-agent systems in LangGraph, CrewAI, and AutoGen and pick a framework with a clear matrix
⚡ Connect and author MCP tools and use agentic RAG as retrieve-then-act, not prompt stuffing
⚡ Add layered guardrails, trajectory evaluation, traces, and cost/latency observability
⚡ Package, budget, and ship an ops-exception multi-agent capstone with golden-set evals
⚡ Name and run practice files from section source zips that match on-screen code
⚡ Judge when not to use an agent — and defend autonomy level to technical and business stakeholders
Requirements
❗ Intermediate Python (functions, modules, virtual environments; async helpful but taught lightly)
❗ Basic experience calling an LLM API (OpenAI-compatible or Gemini) and reading JSON
❗ A computer where you can install Python 3.11+, create a venv, and set API keys in a .env file
❗ Willingness to spend a small amount on API calls or use free/cheap model options when shown
❗ No prior LangGraph, CrewAI, or AutoGen experience required — we build up from scratch