Working classification of chatbot and language-model technologies for AI coaching

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 review), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

The review proposes a working taxonomy of coaching technologies, from rule-based programming (fixed rules and scripted responses) through task-oriented and ML-enhanced NLP/NLU chatbots to early LLMs and mass-market general-purpose LLMs. It distinguishes how systems are programmed (purpose-built versus general-purpose) and used (alone versus with human coaches), noting an AI system performs a coaching function when interaction supports goal clarification, self-reflection, feedback, action planning, motivation, or behavior change. This classification organizes the evidence review and risk analysis.

Accounts

• Working classification of chatbot and language-model technologies for AI coaching: The review proposes a working taxonomy of coaching technologies, from rule-based programming (fixed rules and scripted responses) through task-oriented and ML-enhanced NLP/NLU chatbots to early LLMs and mass-market general-purpose LLMs. It distinguishes how systems are programmed (purpose-built versus general-purpose) and used (alone versus with human coaches), noting an AI system performs a coaching function when interaction supports goal clarification, self-reflection, feedback, action planning, motivation, or behavior change. This classification organizes the evidence review and risk analysis. (Potel et al. (2026))

Claims

• Purpose-built AI chatbot coaching is generally well received and supports short-term motivation and selected behavior change, but effects on sustained, meaningful outcomes are inconsistent [+M]

Related Research Methods

• Curriculum-Instruction-Assessment triad taxonomy of AI educational purposes in VET
• Three-tiered classification system of self-regulation: categories, domains, and facets

Key Sources

• Potel, J. T., & Kumashiro, M. (2026). Artificial Intelligence as a Personal Coach: A Narrative Review of Benefits and Risks in Educational and Health Contexts. Behavioral Sciences, 16(8), 1431. https://doi.org/10.3390/bs16081431

Page metadata

Field	Value
type	research-method
id	working-classification-of-chatbot-and-language-model-technologies-for-ai-coaching
title	Working classification of chatbot and language-model technologies for AI coaching
description	The review proposes a working taxonomy of coaching technologies, from rule-based programming (fixed rules and scripted responses) through task-oriented and ML-enhanced NLP/NLU chatbots to early LLMs and mass-market general-purpose LLMs.
status	review
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.