language models · human-facing systems · 2026 · write-up

Merit Labs

Assessment responses into reports a student can act on.

Site
meritlabs.ai
Status
1000+ tagged questions, 3000+ test-takers
Stack
Next.js, PostgreSQL, containerised CI

What it is

Diagnostic assessment and student analytics. Next.js, PostgreSQL, containerised test infrastructure with CI. An LLM pipeline turning raw assessment responses into individual reports, with prompt architecture and output-quality evaluation iterated against expert feedback rather than against a metric. 1000+ tagged questions, 3000+ test-takers.

The interesting constraint

The reader of the output is a fifteen-year-old and their teacher. A report that is correct and unusable has failed. Evaluating that is not a benchmark problem, and I do not think we solved it.

To writeWhat you tried: the evaluation approach, what worked, what did not.