AI article
The student with the most gaps was getting the longest test
Community description: I'm building a diagnostic tool for A-level maths. A student gives it a question they're stuck on,...
Dev.to | Sep 15, 2026 | Eric Ezenwa
Automated excerpt
An LLM generates a question for whichever skill we're testing; the graph decides which skill to test next. A skill graph is hand-authored, which means it's wrong. Fail one skill and you've queued two more questions.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.