Back to the mapChapterEvaluation & calibrationRubric design, LLM-as-judge grading, gaming resistance, and real-time signal extraction.Tech leadLive skill-tracking system behind a game-like experience scoreA system that continuously reads how well a person is actually performing, independence, quality, communication, speed, and turns that read into an experience-point score that reflects real skill, not just activity.Read moreMajor contributorReal-time mood detector that changes how the AI manager respondsA classifier that reads whether a person is confused, stressed, in a state of flow, or checked out from their recent activity, and uses that read to decide whether their AI manager should be more supportive or more challenging in the next conversation.Read moreTech leadRelationship memory between a person and their AI managerA running record of the working relationship between a person and their AI manager, so a conversation on day ten feels like a continuation of a relationship instead of a conversation with a stranger.Read moreSole authorAutomatic grading system that can't be gamed by blind resubmissionA submission system that reads whatever a person turns in (a document, image, code file, or link), grades it against a rubric, and catches people who resubmit the same broken work hoping it slips through the second time.Read moreSole authorStep-back performance review across a whole project, not just one taskA review that looks across everything a person did across an entire multi-part project, not just one submission, and names the pattern: where they got faster, where they kept stumbling, how they grew.Read moreSole authorTwo quick checks that catch a misunderstood assignment before it wastes daysTwo short understanding checks that run right before someone starts a task, to catch a misread of what's actually being asked before it turns into days spent building the wrong thing.Read moreTech leadRunning narrative that compounds across everything a person doesA continuously updated story of how one person is actually progressing, built from every task, conversation, and submission they complete, so the system remembers the pattern instead of re-reading them from scratch every time.Read moreMajor contributorTwo tools for catching bad AI grading before it snowballsA per-call log of every grading decision the system makes, plus a dashboard that reads that log across many people at once to catch a task that's grading too easily, too harshly, or drifting from what a human would say.Read moreMajor contributorAI manager talks a person through their grading verdict, out loud, pointing at the fileA voice walkthrough where a person's AI manager reads their grading verdict out loud, pointing at the exact spot on their submitted file each comment is about, instead of leaving them to parse a written report alone.Read more