Course Lessons

Course overview, the "two out of three" framework, and how this course works

Learn Git basics, its history (Linus Torvalds), and why version control matters. Cover GitHub, GitLab, Gitea, and more.

What IDEs are and how to use them. Jesse uses Cursor (we will too), but you can also use VSCode, Zed, Continue, Loveable, etc.

Step-by-step guide to setting up Cursor, the AI-powered editor we will use throughout the course

Introduction to Figma and Penpot for designing your AI products. Getting started guides for both.

Create your Element account and join the public AIDevQuest channel. Learn about our private members-only community.

What LangChain is, why Jesse loves it, and how it powers AI applications. Your orchestration framework for the course.

Choose from 11 build paths including CMS, chatbot, phone service, website, game, second brain, and more

Product management is value management. Understanding Agile, Lean, Scrum, Kanban, OKRs, roadmapping, and vision vs mission.

Learn to identify problems worth solving and frame objectives that matter

Create a 1-page brief with user stories and success metrics

Transform your brief into a focused product requirements document

Role assignment, constraints, few-shot learning, chain-of-thought

JSON schemas, validation, and ensuring consistent AI responses

Build a versioned prompt pack with contracts and failure modes

Deep dive into all major providers: ChatGPT/OpenAI, Claude/Anthropic, Together AI, Hugging Face, Gemini, Grok, WebLLM, Mistral, LLaMA, and more

Making smart decisions for your use case and constraints

Document your model choice with reasoning and benchmarks

Embeddings, vector stores, and retrieval-augmented generation

Optimizing your knowledge base for accuracy and source attribution

Understanding vector databases for semantic search and RAG - Pinecone, Weaviate, Qdrant, ChromaDB

Hands-on: create a working knowledge base with answer sourcing

Building learning agents with Pinecone + RAG + LangChain that improve over time with per-user insights

How LLMs can call external tools and APIs

Retries, validation, and preventing tool misuse

Add web search, calendar, and data access to your AI

Building helpful, context-aware conversational interfaces

Multi-step completion, logs, and autonomous workflows

Convert a chatbot flow into an autonomous task agent

Roles, delegation, and coordination patterns

Managing state and communication between agents

Researcher + Writer + QA agents working together

Software development lifecycle adapted for AI products

Turn your PRD into actionable sprints and demos

Deploy your prototype and create your roadmap

Building test suites for AI application quality

Preventing quality degradation and managing API costs

Create pass/fail thresholds and improvement plans

Protect against common AI security vulnerabilities

Implement 5 baseline controls before going live

What to do before charging money for your AI product

Why interoperability matters and the landscape of AI protocols

Facilitating integration of models and tools in AI systems for context-aware generative agents

Enabling autonomous agents to communicate and coordinate in multi-agent systems

Dynamic, personalized UIs that evolve based on user interactions and preferences

Running LLMs directly in the browser for privacy and offline capabilities

The importance of open standards for AI interoperability and the future of the web

Hands-on: Build a context-aware AI system using Model Context Protocol

Hands-on: Implement agent-to-agent coordination and communication patterns

Hands-on: Create dynamic, adaptive interfaces that evolve based on user interactions