Skip to content

Teachy Mini: a knowledge-based generative social robot tutoring prototype on the Reachy Mini platform

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 causal), q2 · 1 of 1 report an effect size · 2 claims rest on one study

Description

Teachy Mini is a generative social robot tutoring prototype built on the open-source Reachy Mini desktop platform, supporting spoken dialogue and head/antenna social cues via the OpenAI Realtime API. The authors "usedthreemainmethodstoprovidetherobotwiththerequiredknowledge:Dynamic system prompting, retrieval-augmented generation, andstateful prompt orchestration". It personalizes through a seven-question onboarding profile, retrieves uploaded PDF lecture slides for grounded explanations, detects conversational states (frustration, confusion, requests for depth) via regex, and injects state-specific instructions such as rephrasing explanations with a concrete analogy. Implementation code is on GitHub and materials on researchbox.org (ID: #8129).

Design Implications

Context

Requirements

  • Requires an external knowledge source for RAG grounding, an onboarding conversation to build the learner profile, and predefined verbal patterns for state detection.

Constraints

  • Designed as an experimental single-session implementation, not a fully deployable educational system; learning progress was only partly accounted for and only the study-buddy role profile was evaluated.

Target Learners

  • university students and recent graduates in single-session tutoring interactions

Learning Goals

  • learning lecture content (research methodologies) through slide-grounded explanation, Socratic questioning, and personalized scaffolding

Claims

Examples

-

Key Sources

  • Stephan Vonschallen, Karim Kaufmann, Dominique Oberle, Friederike Eyssel, Theresa Schmiedel. (2026). Teachy Mini: Development and Preliminary Evaluation of a Knowledge-Based Generative Social Robot for Higher Education. arXiv. https://arxiv.org/abs/2607.22345
Page metadata
Field Value
type design
id teachy-mini-gsr-tutoring-prototype
title Teachy Mini: a knowledge-based generative social robot tutoring prototype on the Reachy Mini platform
description Teachy Mini is a generative social robot tutoring prototype built on the open-source Reachy Mini desktop platform, supporting spoken dialogue and head/antenna social cues via the OpenAI Realtime API.
status review
generated by process:settle-candidates on 2026-10-12
trust unverified — no one has confirmed this page's content
sources 1 — stephan-vonschallen-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.