Search and Filter

ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI

Date

AI Overview

Why it matters

Classroom observation effectively supports teacher growth, but traditional coaching remains limited by high costs, coach shortages, and subjective evaluations. Generative multimodal AI offers a way to deliver scalable, standards-aligned instructional feedback across full lessons.

Study at a glance
  • Question: How can multimodal AI provide reliable classroom observation feedback, and how do teachers perceive its usefulness?
  • Setting and data: United States; 75 PK-12 teachers surveyed, 6 high school educators interviewed, and 6 secondary teachers in a role-play study using ATLAS videos.
  • Method: Multi-phase design-based research with online survey, semi-structured interviews, system development, benchmark evaluation, and simulated-user role-play study.
  • AI tools: ClassMind, AVA-Align, Gemini-2.5-Flash, Gemini-2.5-Pro, Whisper-Large-v3, pyannote 3.1
Key findings
  • The AVA-Align video agent achieved 100% factuality and higher significance and feasibility scores than Gemini-2.5-Pro and Deep Video Discovery when evaluated on ten classroom videos.
  • Six secondary teachers rated the prototype as highly usable overall, reporting manageable cognitive workloads focused on sense-making rather than navigation.
  • Novice teachers favored brief, supportive tips for immediate planning, while experienced teachers sought more critical, comprehensive critiques to challenge established classroom habits.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

Classroom observation -- one of the most effective methods for teacher development -- remains limited due to high costs and a shortage of expert coaches. We present ClassMind, an AI-driven classroom observation system that integrates generative AI and multimodal learning to analyze classroom artifacts (e.g., class recordings) and deliver timely, personalized feedback aligned with pedagogical practices. At its core is AVA-Align, an agent framework that analyzes long classroom video recordings to generate temporally precise, best-practice-aligned feedback to support teacher reflection and improvement. Our three-phase study involved participatory co-design with educators, development of a full-stack system, and field testing with teachers at different stages of practice. Teachers highlighted the system's usefulness, ease of use, and novelty, while also raising concerns about privacy and the role of human judgment, motivating deeper exploration of future human--AI coaching partnerships. This work illustrates how multimodal AI can scale expert coaching and advance teacher development.