// series · 7 parts
Building an AI Assessment System
A field build of AI-graded assessment — grading written answers, testing the judge, red-teaming it, and measuring what actually moved the needle for students. Read in order.
- [ 01 ] The AI Tutor Everyone Builds Is the One Students Ignore
- [ 02 ] Grading Written Answers with an LLM, Properly
- [ 03 ] Your LLM Judge Needs a Test Suite
- [ 04 ] Students Are Adversaries: Red-Teaming an LLM Grader
- [ 05 ] The Grader Was Right and the Students Quit Anyway
- [ 06 ] The Biggest Effect Size Was the Boring Feature
- [ 07 ] Instrument Like a Learning Scientist