Great idea and execution but the design language seems like general llm-generated tailwind. I think you guys are missing a huge opportunity to make the design reinforce the product positioning.
I worked a lot with designing and implementing agentic grading at my job, there's a ~0 chance that on a rubric with 180 items, changing 1 char out of 6000 words would result in a flip in 10+ grading items :)