Learn AI Engineering
Structured courses, deep-dive articles, and hands-on exercises.
How to use this
Follow the learning path
Courses are ordered — Phase I through IV. Start at Git & Python, then move to LLMs, data science, and production systems. Don't skip ahead.
Go deep with guides & articles
When you hit a topic you want to master — RAG, agents, embeddings — pair it with a deep-dive guide or article. These go beyond the course material.
Build something real
Every course ends with a project. Don't move on until you've shipped it. Reading is not learning — building is.
Courses
All coursesAI Automation — Production Agents & Agentic Systems
Build production AI agents from first principles: agent architectures, tool use, multi-step planning, multi-agent systems, memory, guardrails, observability, and enterprise deployment. Go beyond demos to systems that reliably automate real work.
Claude Code Superpowers: AI That Gets Smarter With Every Task
Turn Claude Code from a reactive assistant into a proactive engineering partner. Learn to install and wield the Superpowers skill system — discipline protocols, domain intelligence, persistent memory, and multi-agent coordination — so your AI compounds knowledge instead of starting from scratch every session.
Data Analysis with Python — Expert Practitioner Track
A practitioner-level course covering everything a world-class data analyst does: project scoping, data quality, cleaning, wrangling, EDA, feature engineering, statistical analysis, advanced visualisation, insight generation, and professional reporting.
Data Science Fundamentals — From Theory to Production Models
Master the mathematical, statistical, and algorithmic foundations that every production data scientist depends on. Covers probability, distributions, regression, classification, clustering, model evaluation, explainability, and end-to-end pipelines.
Git Fundamentals — Version Control for Every Developer
Master Git from the ground up — commits, branches, merges, rebases, and collaboration patterns used by professional engineering teams. Practical exercises at every step.
GitHub for Developers — Collaboration, CI/CD & Open Source
From creating your first repository to automating workflows with GitHub Actions — learn how professional teams collaborate on GitHub. Covers pull requests, code review, issues, project boards, secrets management, and CI/CD pipelines.
Introduction to Large Language Models
A hands-on course for engineers who want to understand how LLMs work under the hood and build real applications with them.
Machine Learning Engineering — Production ML Systems
Build ML systems that actually ship: data pipelines, training infrastructure, experiment tracking, model packaging, inference serving, monitoring, and CI/CD for ML. Everything a senior MLE needs to take a model from notebook to production.
Python Mastery — From Zero to AI Engineering
A complete Python course built for developers who want to reach expert level. Starts from first principles, builds through data structures, OOP, and advanced patterns, then dives into NumPy, Pandas, scikit-learn, PyTorch, and production AI application development. Every lesson includes runnable code directly in the browser.
RAG Engineering — Production Retrieval-Augmented Generation
Design, build, and ship production RAG systems from first principles: document processing, chunking strategies, embedding models, vector databases, retrieval quality, query transformations, reranking, evaluation, advanced architectures, and production operations.
Deep-Dive Guides
All guidesComplete AI Development Environment Setup
Set up a professional AI engineering workspace from scratch — Python, VS Code, Jupyter, virtual environments, and your first Groq API call.
Deploying ML Models to Production
A complete playbook for taking a trained model from your laptop to a production API — serialisation, FastAPI, Docker, monitoring, and CI/CD.
Build a Production RAG Pipeline From Scratch
Go from zero to a production-ready Retrieval-Augmented Generation system — chunking, embeddings, vector search, reranking, and evaluation.
Recent Articles
All articlesBuilding Reliable AI Agents: Tool Use, Error Recovery, and State Management
A production engineer's guide to AI agents that actually work — structured tool calling, graceful error recovery, conversation state, and the hard lessons from shipping agents.
Fine-tuning vs RAG: The Engineering Decision Framework
When to fine-tune a model, when to use RAG, and when to combine them — a practical decision framework with cost analysis and real-world tradeoffs.
LLM Inference Optimization: KV Cache, Batching, and Quantization
The engineering playbook for making LLM inference fast and cheap — KV cache mechanics, continuous batching, speculative decoding, and quantization tradeoffs.
Vector Databases in Production: HNSW, IVF, and Choosing the Right Index
A deep technical comparison of HNSW and IVF vector indices — how they work, when each shines, and the operational tradeoffs that matter at scale.