Do you have a grasp of basic LLM principles but struggle to put it all into code? Tired of scattered documentation, outdated tutorials, and frameworks that impress in demos but collapse in production?

You’re not alone. Building with large language models doesn’t have to be confusing - it can be clear, structured, and deeply rewarding.

In this course, you’ll build real LLM-powered apps, one line of code at a time. You'll see how an app is built from scratch in real time, and follow along. Along the way, you'll discover not only how to implement these systems, but the why behind each line of code.

From chatbots to agents and RAG to evals, you’ll learn the core concepts of building atop LLMs. More importantly, you’ll get how LLMs “think” - allowing you to guide them to do what you want despite their nondeterministic nature. Additionally, you’ll be able to balance quality, latency, and cost, making big-picture decisions about AI-powered app architecture. 

AI engineering isn’t just another branch of software development - it’s a different mindset altogether.

Unlike most areas of software engineering, which extend well-understood coding principles, AI engineering breaks the mold. It demands an entirely new way of thinking - one that challenges traditional logic and redefines how you approach building with code.

You’ll discover how to:

⚡︎ Engineer context and retrieval systems so your AI can understand and use your proprietary data.

⚡︎ Build custom chatbots that answer organization-specific questions and help users solve real problems.

⚡︎ Design intelligent agents that research, reason, and take action autonomously.

⚡︎ Level up your prompt engineering so the model follows your intent - not its own.

⚡︎ Use evaluations to continuously monitor LLM output quality.

⚡︎ Embrace the AI-engineering mindset to harness LLM power to achieve your goals no matter the application.

By the end, you’ll have a repeatable, end-to-end framework for creating AI applications that are stable, adaptable, and grounded in real-world principles - not hype. When the next trend hits, you’ll have the foundation to evolve with it, not chase it.

~~~~~~~~~~~~~~~~~~

COURSE DETAILS

~~~~~~~~~~~~~~~~~~

This course is taught live over Zoom by Jay Wengrow, author of A Common-Sense Guide to AI Engineering. You'll receive a free ebook copy, as this course and the book complement each other for a complete learning experience. However, reading the book is not strictly required for the course.

Rather than merely being lectured to about theoretical concepts, you'll watch and follow along as Jay builds LLM-powered apps from the ground up, one line of code at a time. Along the way, he'll show you not just what to do, but explain why we're doing it, building up deep understanding and intuition of how LLMs behave so you can tame them no matter what you're building.

The live classes will be recorded, so you can watch/rewatch them at any point. You'll have access to these videos on the Maven platform forever.

In addition to the live lectures, you'll receive three optional weekend projects so you can put your newfound skills into practice. Hands-on work is key for mastering the skills taught in this course. You'll also use real-time messaging to communicate with Jay and cohort peers.

~~~~~~~~~~~~~~~~~~

COURSE OUTLINE

~~~~~~~~~~~~~~~~~~

Session #1: Getting Started with LLMs

▻ Understanding how LLMs work

▻ Wrangling with the challenges of nondeterminism

▻ Selecting an LLM and augmenting prompts

Session #2: Building a Chatbot

▻ Multi-turn dialogue and conversation history

▻ Adding the system prompt

▻ Augmenting an LLM with knowledge

▻ Working with long context and its associated challenges

Session #3: RAG

▻ Working with semantic-search engines

▻ Preparing a search engine with data prep and ingestion

▻ Measuring recall and precision

▻ Integrating semantic search into the chatbot

Session #4: Evals

▻ Open coding

▻ Axial coding

▻ Creating an eval framework

▻ Running evals

Session #5: Prompt and Context Engineering

▻ Specificity and few-shot prompting

▻ Sequencing and delimiter usage

▻ Techniques for reducing hallucinations

Session #6: Agentic Systems

▻ Tool use/function calling

▻ Running an agent loop

▻ Reducing nondeterminism with agentic workflows

▻ Agentic RAG