Learn to build real software, AI and data systems.
Practical series on software engineering, AI and data. Written by an engineer who has trained, fine-tuned and shipped AI systems, taught at university, and explained it all to 20,000+ learners on Wizard LK.
Series
Each series is a path you can follow from part one, or dip into when you need it.
AI Engineering, End to End
The whole AI toolkit, not just chatbots. Classic machine learning, NLP model training, fine-tuning LLMs and multimodal models, retrieval, agents and evaluation, built the way they are built at work.
- Machine learning
- NLP
- Fine-tuning
- LLMs
- Agents
- Evaluation
Data Engineering, Practically
How data actually moves. ETL and ELT, connectors, warehouses, dbt, orchestration with Airflow and the pipelines that feed analytics and AI.
- ETL & ELT
- Airbyte
- dbt
- Airflow
- Warehousing
All levels
AI Native Development
How software engineering changes when AI agents write much of the code. Thinking for yourself, deciding how much rigour a system needs, harness and context engineering, and reviewing AI-generated work.
- Critical thinking
- Code quality
- Harness engineering
- Context engineering
- Code review
Latest
AI Native Development · Part 6
AI Software Factory — How Is Software Development Changing?
Connect AI agents, automated tools and human oversight into a repeatable workflow across the software development lifecycle, and improve the system that builds your software.
AI Native Development · Part 5
Code Review and Review Tax in the Agentic AI Era — Does Every PR Need the Same Review?
AI can generate pull requests quickly. Getting those changes safely into production requires review effort that matches their risk.
AI Native Development · Part 4
AI Coding Agents and the Doom Loop — The Real Cost of Poor Context
When an agent keeps changing code without solving the problem, the missing ingredient may be relevant, current and trustworthy context.
AI Native Development · Part 3
AI Harness Engineering — Software Engineering Beyond the Prompt
A capable model alone does not guarantee reliable software. Its tools, context, execution environment and controls matter too.
AI Native Development · Part 2
Does Every Piece of Software Need the Same Code Quality in the AI Era?
The skill is deciding how much engineering effort each piece of software needs, based on its lifespan, dependencies and consequences of failure.
AI Native Development · Part 1
Are You Becoming a ‘Meat Proxy’ in the AI Era?
Getting answers from AI and truly understanding them are two different things. What value do we add when we simply pass questions and answers along?