New
AI & ML Engineering
From your first API call to a multi-agent system in production
60 lessons · 20h 22m
Created by Demo TrainerUpdated September 2026EnglishIntermediate
What you'll learn
- Explain what a language model is actually doing, in terms you can defend in an interview
- Call an LLM API from Python with memory, streaming and function calling
- Build an agent from scratch — tool calling, ReAct, planning and reflection — before reaching for a framework
- Orchestrate several agents with shared memory, routing, retries and human approval
- Build stateful agent workflows in LangGraph with real tools and sub-agents
- Choose a model on cost and capability rather than on fashion
- Ship a finished AI Career Coach with a working interface
- Level
- Intermediate
- Duration
- 60 lessons (about 12 weeks)
- Material
- 20h 22m
- Lessons
- 60
- Language
- English
- Access
- 365 days
About this course
Sixty lessons that take you from what a language model actually is to a working multi-agent AI Career Coach — agents built from scratch first, then LangChain and LangGraph once you know what they are replacing.
Most AI courses teach you to prompt. This one teaches you to build. You start with the vocabulary used precisely — AI against ML against deep learning against generative and agentic — then make your first API call, add memory, add streaming, and write an agent from scratch in plain Python so that when LangChain and LangGraph arrive you already know what they are doing for you. The second half is multi-agent work: orchestration, shared memory, routing, retries, tracing, human approval and parallel execution, finished as an AI Career Coach with a real interface. It closes on the Claude model family and choosing a model on cost and capability rather than on whichever one was in the news.
Syllabus
8 modules · 60 lessons · 20h 22m · 1 free to preview
Start here
- 100 Days to Master AI Engineering | LangChain, RAG, Agents & More
- How to Become an AI Engineer in 100 Days | Practical Roadmap
AI foundations
- AI vs ML vs DL vs GenAI vs Agentic AI
- LLMs & Tokens Explained
- Tokens, Context Window & Parameters Explained
- Comparing LLM Models | ChatGPT vs Gemini vs Claude
- Prompt Engineering Fundamentals | RTCFO Framework
- Advanced Prompt Engineering Techniques
Working with LLM APIs
- APIs Explained for AI Engineers | Gemini API Key Setup
- Connect Gemini API with Python | Google AI Studio Tutorial
- Build a Conversational AI Chatbot with Memory | Gemini API + Python
- Streaming AI Responses in Python | Real-Time AI Chatbot
Building your first agents
- AI Tool Calling Fundamentals in Python | MCP & AI Agents Foundation
- Build Your First AI Agent in Python | Assistant vs Agent Explained
- Building Autonomous AI Agents | LLM-Based Tool Decision Making
- Function Calling with Gemini | Build an AI Career Assistant in Python
- ReAct Agent in Python | Build Your First AI Career Coach Agent
- Planner Agent in Python | Build an AI Career Planner Agent
- Build a Research Agent with Python
- Build a Reflection Agent with Python
Multi-agent systems
- Build Your First Multi-Agent AI System
- AI Agents Collaborating in Real-Time
- Multi-Agent Orchestration with Python
- Conversation Memory for Multi-Agent AI Systems
- Build a Knowledge Base for AI Agents
- Workflow Routing Changes Everything in Multi-Agent AI
- Retry Failed AI Agents Automatically
- Track AI Agent Execution with Python
- Human-in-the-Loop
- Parallel Agent Execution: The Speed Hack Every AI Engineer Needs
- AI Career Coach Studio with Streamlit
- AI Career Coach Project Wrap Up
LangChain
- LangChain Tutorial for Beginners | Introduction & Setup
- Your First LangChain Program - Gemini API Setup & .env
- Build an AI Coding Assistant - LangChain Prompt Templates
- LangChain LCEL & Output Parsers Explained | AI Coding Assistant
- LangChain LCEL Pipeline - Prompt to Model to Parser
- LangChain Runnable Interface - Lambda, Parallel & Branch
- Context Management in LangChain | AI Engineering Day 37
- Build Multiple Chains in LangChain | AI Engineering Day 38
LangGraph
- Beyond LangChain: Why You Need LangGraph
- LangGraph Tutorial | Graph, Node, Edge, State Explained + First LangGraph Program
- Build a Multi-Node Workflow with LangGraph | AI Engineering Day 41
- Conditional Edges in LangGraph Explained | AI Engineering Day 42
- Don't Build AI Without Pydantic | Agentic AI with LangGraph | AI Engineering Day 43
- Why AI Agents Need Tools | Tool Calling in LangGraph
- Build Your First Real Tool in LangGraph | Project Context Tool
- Build a Custom File Reader Tool in LangGraph | AI Engineering Day 46
- LangGraph Sequential Workflow: Build a Multi-Tool Agent
- Parallel Tool Execution in LangGraph | Fan-Out & Fan-In Explained | AI Engineering Day 48
- Build a Multi-Agent System in LangGraph | AI Engineering Day 49
- Agent Orchestration in LangGraph | Supervisor & Worker Agents | AI Engineering Day 50
- Sub-Agents & Subgraphs in LangGraph | AI Engineering Day 51
- Memory & Checkpointing in LangGraph | AI Engineering Day 52
Claude and certification
- Master 3 Claude Certifications in One Series
- What Is Claude AI? Ecosystem & API Setup for Beginners
- Claude Haiku vs Sonnet vs Opus: Which Model Should You Use?
- Claude Dynamic Model Routing in Python | Cut Cost Without Losing Quality
- CCAO-F Exam Prep | Claude AI Capabilities & Limitations | What It Can and Cannot Do
- Testing Claude Capabilities & Limits using Python
Your instructor
Full-stack engineer, and the person who built this platform
Fifteen years building and running production systems, most of them in Java and JavaScript. Teaches the way he works: start with something that runs, then make it correct, then make it fast.
What you'll get
- Free first lessonThe opening lesson of the course is public — read it before you buy.
- Lifetime accessOne purchase, a year of access, and every future update included.
- Every lesson on videoRecorded, chaptered and rewatchable at your own speed.
- Certificate on completionIssued automatically and verifiable by a public link.
Tools you'll use
- PythonThe whole series is written in it — no notebook-only code
- Gemini APIKeys, requests, streaming and function calling
- LangChainPrompt templates, LCEL, output parsers and chains
- LangGraphState graphs, conditional edges, tools and sub-agents
- PydanticTyped, validated inputs and outputs for every agent
- StreamlitPutting an agent behind an interface people can use
- Claude APIModel selection, dynamic routing and cost control
Before you start
- Comfortable writing basic Python — functions, dictionaries, a virtual environment
- A laptop that can run Python 3.10 or newer
- A free Google AI Studio key; every paid service used has a free tier
Who this is for
- Developers moving into AI engineering from ordinary backend or web work
- Data people who can train a model but have never served one
- Anyone who has used ChatGPT and wants to build with it instead of in it