The craft of AI Engineering
Practical training for software engineers building with AI — as a coding tool, as a product capability, or both.
Pre-order 10 Prompts in 10 Days — 25% off launch price
One prompt framework per day with a hands-on exercise to practice. Launches June 1.
Where we meet you
Go from demos to real workflows. You've got Claude Code or Cursor installed. The demos look incredible. The next step is building the habits and workflows that make AI tools productive every day — scoping tasks for agents, reviewing generated code with confidence, and knowing when to steer versus when to step back.
Ship AI-generated code you actually trust. Agentic coding is fast. The craft is learning to verify, scope, and maintain what agents produce. You'll build the discipline to move quickly and still understand what's going into production.
Take AI features from prototype to production. The LLM call works in testing — that's the starting line. We'll work through what comes next: latency, costs, failure modes, evaluation, and maintenance. You'll learn to ship AI features that hold up in the real world.
Training that starts where tutorials end
Every course is built from real workflows. You'll practice the workflows that actually make AI productive in real software — scoping tasks, reviewing generated output, integrating AI features, and choosing the right tool for the job.
Learn by doing. Courses are structured around practical exercises and real-world scenarios. You'll write working code, make implementation decisions, and walk away with skills — and artifacts — you can bring back to your team.
What engineers are saying
"I thought the training was excellent in all respects. I especially appreciated the informal Q&A that ran through the whole thing, where your expertise shone through and your relaxed, informal style made everyone comfortable asking the simplest questions."
Colm O'Cinneide, PhD
Professor of Mathematics, Columbia University
"He understands how to teach a large audience and is able to adapt his delivery to the members of the class."
Kate Strachnyi
Story By Data · LinkedIn's Top Voice in Data Science
"As a data scientist with nearly four years of experience in the field, I was able to walk away from the session with a few new tips and tricks under my belt. The package is an all-around excellent bundle taught by a talented and experienced data engineer, analyst, and scientist."
Jane Thompson
Manager of Analytics - Voltus
Built by a practitioner
I've spent fifteen years building software and leading engineering teams — most recently co-founding .txt to build LLM structured generation infrastructure. Prior to .txt, I led the team that built Outlines, an open-source library now widely used for structured LLM output. I've taught thousands of engineers through O'Reilly Media courses on Python, data engineering, and machine learning. I started Abilezi because the training I kept looking for didn't exist: practical training for engineers building with AI — as a coding tool, as a product capability, or both.
Pre-order 10 Prompts in 10 Days — 25% off launch price
One prompt framework per day with a hands-on exercise to practice. Launches June 1.