TeachingCoach¶
Product or Programme · All products and programmes
Evidence · 1 claim (1 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 1 claim rests on one study
Description¶
TeachingCoach is an AI-based conversational coaching system developed by Isabel Molnar and colleagues to help higher-education instructors diagnose teaching challenges, develop strategies, plan next steps, and reflect through evidence-grounded multi-turn dialogue.
Components¶
- TeachingCoach data-centric pipeline: rule extraction, synthetic dialogue generation, expert filtering, and fine-tuning: TeachingCoach is built through a pipeline in which experts extract pedagogical rules from authoritative education resources, GPT-4o generates teacher profiles, teaching challenges, and multi-turn synthetic dialogues, human experts filter the dialogues, and the curated data fine-tune a LLaMA-2-13B-Chat model. The article states that "experts extract 36 core instructional rules and encode them as structured system prompts," anchoring conversations in evidence-based practices. Dialogues progress through clarifying the challenge, exploring strategies, planning next steps, and reflecting. (Isabel Molnar et al. (2026))
Claims¶
Related Products and Programmes¶
Key Sources¶
- Isabel Molnar, Peiyu Li, Si Chen, Sugana Chawla, James Lang, Ronald Metoyer, Ting Hua, Nitesh V. Chawla. (2026). TeachingCoach: A Fine-Tuned Scaffolding Chatbot for Instructional Guidance to Instructors. https://arxiv.org/abs/2603.18189
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
teachingcoach |
title |
TeachingCoach |
description |
TeachingCoach is an AI-based conversational coaching system developed by Isabel Molnar and colleagues to help higher-education instructors diagnose teaching challenges, develop strategies, plan next steps, and reflect through evidence-grounded multi-turn dialogue. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.