Building with AI
From a working prototype to a system you can trust in production.
Seven chapters on the engineering around the model — the 95% of the work that turns an impressive demo into a product. Each pairs a plain-language explanation with optional dive-deepers into the code and the research.
Written for engineers and technical builders. You don't need an ML background — the load-bearing skills here are backend engineering, API design, and testing.
Chapters
- Chapter 01 · 10 min
The shape of an AI feature
“A power tool needs a workbench. The model is the blade; the system is everything that keeps your fingers attached.”
Read → - Chapter 02 · 11 min
Prompts as software
“A prompt isn't a wish you whisper to a genie. It's a spec you hand to a contractor.”
Read → - Chapter 03 · 13 min
Retrieval done right
“Don't make the model memorise the library. Hand it the three pages it needs, opened to the right paragraph.”
Read → - Chapter 04 · 11 min
Tools & function calling
“Stop asking the model to do arithmetic in its head. Give it a calculator and let it press the buttons.”
Read → - Chapter 05 · 12 min
Agents that don't fall over
“An agent is an intern with a to-do list and a phone. Useful for errands; dangerous with your credit card.”
Read → - Chapter 06 · 12 min
Evals & observability
“An eval is the smoke detector. Annoying until the night it saves the house.”
Read → - Chapter 07 · 12 min
Shipping & operating
“Shipping a model is not launching a rocket. It's opening a kitchen — the hard part is the lunch rush, every day.”
Read →