Classroom Observatory
Classroom Observatory is a teacher-facing agent. It notices participation, confusion, and momentum during class, and the teacher decides what those signals mean.
| A score of the student | Classroom Observatory | |
|---|---|---|
| What it reports | A grade, a rank, or a hidden risk score. | Participation, confusion, and momentum, offered while the class is still happening. |
| Who interprets it | The software names a judgment. | The teacher keeps the interpretation of the room. |
| What it may collect | Face video, keystroke logs, or a score the family cannot see. | A signal the teacher can use in the next minute and explain to a family. |
An agent for the teacher
In a busy class, attention is scarce. A teacher can miss a quiet student who is stuck because the visible activity is somewhere else. Classroom Observatory watches for a small number of signals and offers them as a prompt while the class is still happening.
Participation is about who has had a chance to contribute, not who talked the longest. Confusion is about where an explanation failed. Momentum is about whether the work is moving. None of these is a grade.
What the agent may use
A signal should be something the teacher can act on in the next minute, and something the teacher can explain. Video of faces, keystroke logs, and hidden scoring are outside the brief. If a family cannot understand the sentence that describes the signal, the agent should not collect it.
Teachers shape the instrument
Educators decide what counts as confusion in a discussion, which is not the same thing as confusion in a lab. Those distinctions are written in Writing when there is a source a reader can check. NexEd describes the limit on the About page.
Writing on this program
- Apprenticeship Thinking for AI Classroom Agents
Legitimate peripheral participation explains how learners move from observation to mastery within a community, offering a framework for AI agents that coordinate classroom work. This essay explores how teachers and designers can use situated learning principles to build AI tools that support authentic practice rather than isolated drill.
- Feedback Timing in AI Classroom Agents
This essay examines how the timing and granularity of feedback from AI agents shapes student learning, drawing on research into intelligent tutoring systems. It is written for teachers and researchers evaluating AI tools that assist instruction or coordinate classroom work.
- Learner Agency in AI Classroom Agents
This essay examines how artificial intelligence agents in education can preserve learner agency, drawing on UNESCO guidance and self-determination theory to inform design choices for teachers and researchers.
- How to Use WebAI Principles for Student Data Privacy
Learn how to configure browser-based local AI models using techniques aligned with WebAI to keep student data private in classroom web apps without relying on cloud servers.