Generative AI: From Models to Agents
Generative AI: From Models to Agents is a course on taughtful.ai, taught lesson by lesson by a free voice AI tutor that explains each lesson out loud and generates its video in real time. Modern generative AI from the ground up: how LLMs work, then prompting, context engineering, RAG, agents, MCP and Claude Code, one lesson at a time. It has 8 lessons, 2 quizzes, 1 game and 1 spoken check, about 1 hour in total.
Generative AI: From Models to Agents: 8 lessons taught out loud by a voice AI tutor you can interrupt with any question.
What the course gives you
- 8 lessons that build one mental model, from next-token prediction to agents that take real actions.
- A voice AI tutor explains each lesson out loud, generates its video in real time and answers any question you ask mid-lesson.
- Real video clips inside the lessons, plus quizzes, games and a spoken check where you explain the ideas back.
What you will be able to do
- Explain what an LLM actually does: predict the next token, inside a limited context window.
- Write prompts that give reliable output: a specific task, a few examples, step-by-step reasoning and an exact output format.
- Describe how RAG grounds answers in your own documents: index, retrieve, augment, generate.
- Explain how AI agents plan, act and observe with tools, and how MCP plugs those tools in.
What you will learn
- Generative AI & LLMs
- Prompt Engineering
- Context Engineering
- Retrieval-Augmented Generation (RAG)
- AI Agents
- Model Context Protocol (MCP)
- Claude Code
- Best Practices with LLMs
What the course includes
- 8 lessons, each taught out loud
- 2 quizzes
- 1 game
- 1 spoken check where you explain the idea back in your own words
- About 1 hour in total
Checkpoints along the way
- Check: Foundations
- Game: Hunt the Vocabulary
- Explain it back
- Check: Agents, MCP & Claude Code
How the course is taught
Each lesson is taught by a voice AI tutor. It explains the lesson out loud and generates the lesson's video in real time, and you can interrupt it at any moment with any question. Between lessons, checkpoints make sure you understood: quizzes, and spoken checks where you explain the idea back in your own words. Progress is saved, so you pick up exactly where you stopped.
Who it is for
Anyone who uses AI tools and wants to understand what is underneath them: students, builders, product people and the curious. No coding required.
Why teaching this way works
- One-to-one tutoring is the most effective form of instruction ever measured: in Bloom's studies the average tutored student performed about two standard deviations above a conventionally taught class, better than 98 percent of those students. Every lesson in this course has that kind of tutor. (Bloom, "The 2 Sigma Problem", Educational Researcher, 1984)
- People learn more deeply from words and pictures together than from words alone, which is why the tutor generates each lesson's video as it explains instead of only talking. (Mayer, Multimedia Learning, Cambridge University Press)
- Retrieving what you just learned makes it stick far better than going over it again, which is why the course has quizzes and spoken checks between lessons. (Roediger & Karpicke, "Test-Enhanced Learning", Psychological Science, 2006)
Frequently asked questions
What does Generative AI: From Models to Agents cover?
Modern generative AI from the ground up: how LLMs work, then prompting, context engineering, RAG, agents, MCP and Claude Code, one lesson at a time.
What will I learn in Generative AI: From Models to Agents?
8 lessons: Generative AI & LLMs, Prompt Engineering, Context Engineering, Retrieval-Augmented Generation (RAG), AI Agents, Model Context Protocol (MCP), Claude Code and Best Practices with LLMs.
Who is Generative AI: From Models to Agents for?
Anyone who uses AI tools and wants to understand what is underneath them: students, builders, product people and the curious. No coding required.
How long is Generative AI: From Models to Agents?
8 lessons, 2 quizzes, 1 game and 1 spoken check, about 1 hour in total.
Who teaches it?
A voice AI tutor on taughtful.ai. It explains each lesson out loud, generates the lesson's video in real time, and answers any question you ask mid-lesson.
Can I ask questions during a lesson?
Yes. Interrupt the tutor by voice at any moment and it answers, then picks the lesson back up.
How is this different from a video course?
A video course plays the same for everyone. Here a voice AI tutor teaches each lesson out loud, generates the lesson's video in real time, stops to answer whenever you interrupt, and checks you understood before you move on.
Is my progress saved?
Yes. Your progress is saved, so you pick up exactly where you stopped.
Can I take it at my own pace?
Yes. Stop after any lesson and come back whenever you like; your progress is saved, so the course waits where you left it.
Is it free?
Yes to start: 10 voice minutes a day and 25 a week, no card needed. Pro is $15 a month or $144 a year, and Max is $39 a month or $372 a year, so annual billing saves 20 percent.
Published 2026-06-09 · Last updated 2026-09-22 · Written and maintained by the taughtful.ai team.