Students don't know what to read or how; parents can't see progress; teachers can't follow every child. Tencent built AI Tutor on MOI, using a multi-agent architecture that turns one reading session into a personalised path, interactive Q&A, comprehension testing and knowledge expansion.
Tencent, one of the world's largest technology companies, is developing AI-powered education products addressing China's national push for digital learning and youth reading literacy.
Students don't know what to read or how to read-they find assigned books uninteresting, struggle with comprehension, and get little feedback or sense of progress. Parents lack the expertise to guide their children's reading (69.9% say they need help), and most cannot participate in shared reading. Teachers have no time to run dedicated reading programs, no way to track whether students actually finish books, and often lack deep knowledge of every title on the curriculum. No existing product solves this-the market offers only e-books or exam-focused drill courses, neither of which builds genuine reading ability.
Tencent built AI Tutor on OmniFabric-an intelligent reading companion powered by a multi-agent architecture that guides students through a structured, interactive, and personalized reading journey across modern texts, classical poetry, composition, and cultural literacy.
Students engage with authors as AI-generated personas, explore knowledge graphs, and answer guided questions-transforming reading from a solitary chore into an interactive learning experience.
AI assesses each student's reading ability and generates weekly plans (4 days reading + 1 day open discussion), adapting difficulty and content to individual progress and interests.
Multi-format comprehension exercises (open Q&A, scenario role-play, passage imitation writing) are generated dynamically per article, giving students and parents concrete feedback on learning outcomes.