Measured Academy · Course 1 · Pilot
AI Engineering, Measured
The fifteen chapters of the book as fifteen modules for working developers. Every module ends in a test you pass by running real code and handing in the file it wrote. Every number you see was produced by a run that is saved, and you can open the file it came from.
Start Module 1 Module 1 is free.
- For: Working developers who ship software and are new to building with language models.
- You bring: your own API key. Each module states what its exercise cost on the recorded run, or says plainly that it has not been measured.
- Graded by: a check script you run on your own machine, or a checklist where the module says so.
- Age: 18 or older.
Your progress
Nothing started yet. Progress is kept in this browser only.
How every lesson is built
- What happenedA real run, with its model and date.
- Why it changedThe cause, in plain terms.
- How it is measuredThe instrument, small enough to rerun.
- How to improve itWhat to do differently in your own code.
A value printed like this is a measured result. Hover or focus it to see the file it was read from. Anything marked UNMEASURED has not been run yet, and no figure is shown for it.
Still to come
Modules 5 to 15 follow the remaining chapters of the book. They are outlines today and are not part of this pilot.
- 5 RAG: When to Retrieve, and How to Tell It Failed
- 6 Vector Storage: An Index That Outlives the Process
- 7 Conversation State: What to Keep and What to Drop
- 8 Multi-Agent Systems: When to Split, and When Not To
- 9 MCP: Using Tools You Did Not Write
- 10 Evaluation: Catching Regressions in a System That Won't Repeat
- 11 Security: Bounding What the Model Can Do
- 12 Observability: Tracing What Actually Happened
- 13 Cost: What It Spends, and How to Spend Less
- 14 Streaming, Async, and Jobs: Handling the Wait
- 15 Your Own System: The First Three Moves
Teaching this course?
Measured for Educators is a pilot kit for running this course in your own class: syllabus templates for 12 or 6 weeks, lesson plans, graded labs with rubrics and policy templates. See the kit for educators