Courses

Skip the black-box frameworks. Build a working AI coding agent from scratch in pure Python. Add tools and memory, use cloud or local models, and test it with pytest. All in one file.

"A user reports an app is down. Disk is at 100%. SSH is timing out. What’s your next move?"Stop memorizing endless command lists. Learn how to diagnose, fix, and automate real enterprise Linux environments.📖 Linux System Administration: From CLI Basics to Server Operations 🛠️ Coming soon. Master the terminal, own the server.

Master the 32 essential rules of econometrics—from basic OLS to advanced machine learning and time series forecasting—explained in rigorous, plain English.

Score your Claude Code setup out of 50, then prove it by firing your own hooks by hand and reading the exit code. Six sections, a free MIT-licensed toolkit, and eight dated incidents where the guard failed silently.

Master the future of AI-powered software development with Claude Code. In this hands-on course, you'll learn how to harness Anthropic's agentic coding system to build software faster, write better code, and automate complex development workflows. Starting with the fundamentals and progressing to advanced techniques like prompt engineering, multi-agent collaboration, automation, and security, each lesson includes practical, working examples you can apply immediately. Whether you're just getting started with AI-assisted development or looking to take your engineering workflow to the next level, this course will give you the skills and confidence to use Claude Code effectively in real-world projects.

Transform AI from a buzzword into a business advantage. This course equips leaders with the frameworks, tools, and confidence to identify high-impact AI opportunities and implement them responsibly.

Build powerful AI agents without relying on the cloud. In this hands-on course, you'll learn how to create intelligent, production-ready agents that run entirely on your own hardware using Ollama. Starting with the fundamentals and progressing to advanced topics like RAG, tool calling, long-term memory, and multi-agent systems, you'll develop real-world applications through practical, copy-and-run examples. Whether you're building personal assistants, automation tools, or sophisticated AI workflows, this course gives you the knowledge and code to build fast, private, and reliable AI agents with confidence.

Stop building fragile AI demos. Learn how to design, test, and operate AI agents like real software systems.

Learn Python asyncio from zero by building the event loop by hand. Six fetches go from 12 seconds to 3 on one thread, and you understand every line. Most asyncio tutorials throw async and await at you on page one. This course builds the event loop by hand first, in plain Python, so the keywords finally click. Six fetches drop from 12 seconds to 3, on one thread, and you understand every line. No magic. This interactive course has a companion book, Asyncio Without the Magic, on Leanpub at https://leanpub.com/asyncio . The book is the deep, cover-to-cover read; the course is where you make it stick with quizzes, build-it-yourself exercises, and runnable notebooks. They are built to be used together: read the idea in the book, then drill it in the course until it is yours. You get a lot from either one on its own, and the most by far from both together.

ChatGPT's memory. AI search. RAG. Recommendation engines. All of it stands on ONE idea — and almost nobody using AI actually understands it. This course takes you from absolute zero (no code, no math, no fees) to building your own AI search engine that finds things by meaning. In the age of AI, this is the line between people who prompt and people who build. Which side are you on?

A Cray Research veteran narrates how pioneers handled overwhelming complexity: pattern recognition anticipating Midway, systems thinking inventing magnetic core memory. Experience from one domain, applied in a new way, shaped supercomputing.

What was so unusual and special about Cray Research? We accomplished, repeatedly, what nobody else on the planet was able to match. High-Performance Computing is not merely parallelism and large-scale systems. That is the public-facing decoy version.

Build a real AI assistant system with memory, tools, workflows, scheduling, and safety gates — not just prompts. Finish with a working Department Agent OS you can prove works.