Fine-tuning & EvalsEvalsEdTechFixed budget
Content-QA Agent for a Course Platform
Lumen Learning Studio · Remote (US/EU)
$8k fixed
The outcome
An agent that reviews AI-generated lessons for accuracy and clarity, and scores whether they'll actually teach — a QA gate before publish.
The client
Lumen Learning Studio — Remote (US/EU). A fine-tuning & evals build we delivered end to end.
The challenge
Build an evaluation agent that reviews generated course content against accuracy and clarity rubrics and blocks weak lessons before they ship.
What we built
- Score lessons against accuracy and clarity rubrics
- Flag confusing or wrong content with rationale
- Gate publishing on the eval result
The stack
Stack: LLM-as-judge design, rubric eval, and a publishing integration.
Want something like this?
Tell us what you're building and we'll scope it — most projects start within a week.