You're at the starting line of the course, where Guil sets the foundation for everything that follows and shows what "agentic" behavior actually looks like in practice. This lesson is a guided orientation: what agents are, why prompts alone hit limits, and how Mastra organizes the building blocks.

You'll watch an agent run end-to-end, including how it calls tools, uses prior context for follow-up questions, and how you can tweak behavior by changing models and instructions. You'll also get a clear preview of the project you'll build in this course: a theme park companion that pulls live data, makes recommendations, and can guide a user through multi-step tasks.

This matters because the rest of the course assumes you can distinguish between single-turn chat responses and systems that reliably take actions. Once you understand how tools, workflows, memory, and observability fit together, you'll be able to build features that are testable in development and shippable in production—without guessing what the model "really did."

"I'm Guil Hernandez, and I'll be your instructor for this course. I've spent over a decade building software and teaching it—my courses have reached more than 500,000 learners on platforms like Treehouse, Scrimba, and YouTube. Now I'm all-in on AI agents, and this course is your roadmap. Agents are the next platform shift. The engineers who learn to build them now will shape what comes next."

— Guil Hernandez

Mentioned in the Lesson

Code:

• Course GitHub repo

Relevant Mastra docs:

• Agents Overview
• Using Tools (Agents)
• Workflows Overview
• Human-in-the-loop (Workflows)
• Memory Overview
• Storage (Memory)
• Observability Overview
• Tracing Overview
• Mastra Cloud: Observability
• Deployment Overview

Join the Community

Ask questions:

• Discord — chat with other learners and the Mastra team
• Guil on LinkedIn — ask him questions directly

Follow Mastra:

• X — follow Mastra for updates
• YouTube — watch more tutorials
• LinkedIn — follow for updates