AI
AIBecoming an AI Engineer: Your Recap and What's Next
You've gone from "what is AI?" to building, deploying, evaluating and securing real AI systems. This finale recaps the advanced track, defines what makes you an AI engineer, and shows how to keep growing at the frontier.
AIOn-Device AI: Running Models Locally and Privately
AI doesn't always need the cloud. Learn how to run models on your own phone or laptop — for privacy, zero API cost and offline use — the trade-offs, the tools like Ollama, and a runnable "will it fit?" calculator.
AIMaking AI Faster and Cheaper: Cost and Latency Optimization
LLM apps can get slow and expensive fast. Learn the practical levers that cut cost and latency — right-sizing models, caching, trimming context, streaming and more — with a diagram and a runnable caching demo.
AIMulti-Agent Systems: AI Teams That Work Together
One AI agent has limits; a team of specialists can tackle far more. Learn how multi-agent systems work — specialized roles, orchestration patterns and a critique loop — with a diagram and a runnable researcher-writer-critic demo.
AIMultimodal AI: Models That See, Hear and Speak
Modern AI isn't limited to text — it can see images, hear audio and understand video. Learn how multimodal models work through a shared embedding space, what they can do, and how to use them, with a diagram and a runnable demo.
AILLM Security: Prompt Injection and How to Defend Against It
The moment you give an LLM your data or tools, security matters. Learn how prompt injection works — including the sneaky indirect kind — why it happens, and the layered defenses that keep AI apps safe. A defender's guide.
AIHow to Evaluate LLMs and AI Systems: Is Your AI Good?
An AI that sounds confident can still be wrong. Learn how to actually measure LLM quality — automatic metrics, human eval, LLM-as-a-judge, RAG-specific scoring and hallucination testing — with a runnable eval demo.
AIBuild a RAG App Step by Step: A Hands-On Project
Turn the RAG theory from Lesson 22 into a real, working app. We'll build a "chat with your documents" tool in Python — chunking, embeddings, retrieval and prompting — step by step, with runnable code you can extend.
AIDeploying AI Models: From Notebook to Production (MLOps)
A model in a notebook helps no one. Learn how to take an AI model to real users — saving it, serving it as an API, hosting it — plus the MLOps essentials that keep it alive: monitoring, drift and retraining.