{ "abstract": "Artificial intelligence (AI) chatbots are being explored to deliver health coaching across multiple contexts. However, the quality and safety of chatbot-generated advice is influenced by how prompts are constructed, and prompt design remains inconsistently described in the literature. This scoping review examined how prompt design has been applied and evaluated in AI health coaching chatbots and summarized the study designs, prompt strategies, and outcomes reported across studies. We conducted a scoping review following PRISMA-ScR guidance and searched PubMed, Embase/Ovid MEDLINE ALL, PsycINFO, IEEE Xplore, and Scopus for peer-reviewed studies published up to October 2025. Eligible studies examined prompt design in large language model–based health coaching chatbots. Data were extracted using a standardized form and synthesized narratively. Twelve studies were included, spanning mental health, medication use, physical activity, and nutrition contexts. Study designs were primarily simulation-based, with few involving real users. Prompt strategies were grouped into structural modifications, prompting techniques, and role-based approaches. Structural modifications, such as increasing specificity and adding constraints, were most common and were reported to improve response quality and clarity. Prompting techniques were reported to improve task performance but sometimes reduced focus or consistency. Role-based prompting influenced tone, specificity, and guideline alignment. Outcomes focused mainly on response quality, with fewer studies assessing safety or user experience and only one evaluating clinical outcomes. Prompt design is a key, modifiable determinant of chatbot performance. However, current evidence is limited by heterogeneous study designs and minimal real-world evaluation. Greater focus on prompt design is needed to improve the quality and safety of AI-delivered health coaching and its real-world impact on health outcomes. Author summary: AI chatbots are increasingly being explored to support health coaching, helping people manage their health and make behavior changes across areas such as mental health, physical activity, nutrition, and medication use. A key factor shaping how these chatbots respond is prompt design, which refers to how the instructions given to an AI model are structured and worded. Despite growing interest in AI health coaching tools, little is known about how prompts are designed or how different design choices affect the quality and safety of chatbot responses. In this scoping review, we searched five academic databases and identified 12 peer-reviewed studies examining prompt design in AI health coaching chatbots. We found that most studies used simulated settings rather than real-world testing, and that prompt design strategies influenced the quality of chatbot responses. However, safety and patient experience were rarely evaluated, and only one study measured actual health outcomes. Our findings highlight prompt design as an important but understudied factor in AI health coaching. We hope this review helps guide researchers and developers toward safer, more effective AI tools that are evaluated in real-world settings.", "abstract_shown": true, "affiliations": [ "Department of Health Research Methods, Evidence, and Impact, McMaster University, Hamilton, Ontario, Canada", "School of Medicine, University College Dublin, Dublin, Ireland", "Department of Pediatrics, McMaster University, Hamilton, Ontario, Canada", "Biostatistics Unit, Father Sean O’Sullivan Research Centre, St. Joseph’s Healthcare, Hamilton, Ontario, Canada", "Centre for Development of Best Practices in Health (CDBPH), Yaoundé Central Hospital, Yaoundé, Cameroon", "Division of Epidemiology and Biostatistics, Department of Global Health, Stellenbosch University, Cape Town, South Africa" ], "article_type": "Research Article", "arxiv": null, "author_total": 6, "authors": [ { "affs": [ 0 ], "name": "Taylor Incze" }, { "affs": [ 1 ], "name": "Sahar Khademioore" }, { "affs": [ 2 ], "name": "Alla Bengizi" }, { "affs": [ 3 ], "name": "Lawrence Mbuagbaw" }, { "affs": [ 4 ], "name": "Elizabeth Alvarez" }, { "affs": [ 5 ], "name": "Laura N. Anderson" } ], "bibtex": "https://research.draconitic.com/paper/4fzkspfyhs5r7.bib", "cited_by": 0, "doi": "10.1371/journal.pdig.0001827", "fulltext_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001827", "id": "4fzkspfyhs5r7", "issns": [ "2767-3170" ], "landing_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001827", "language": null, "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "journal", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "plos", "/Biology and life sciences/Nutrition" ], [ "plos", "/Biology and life sciences/Sports science/Sports and exercise medicine" ], [ "plos", "/Biology and life sciences/Sports science/Sports and exercise medicine/Exercise" ], [ "plos", "/Computer and information sciences/Artificial intelligence" ], [ "plos", "/Medicine and health sciences/Mental health and psychiatry" ], [ "plos", "/Medicine and health sciences/Nutrition" ], [ "plos", "/Medicine and health sciences/Public and occupational health/Behavioral and social aspects of health" ], [ "plos", "/Medicine and health sciences/Public and occupational health/Physical activity" ], [ "plos", "/Medicine and health sciences/Public and occupational health/Physical activity/Physical fitness/Exercise" ], [ "plos", "/Medicine and health sciences/Sports and exercise medicine" ], [ "plos", "/Medicine and health sciences/Sports and exercise medicine/Exercise" ], [ "plos", "/Research and analysis methods/Research assessment/Peer review" ] ], "openalex": null, "pdf_url": "https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0001827&type=printable", "pmcid": null, "pmid": null, "published": "2026-11-12", "publisher": "Public Library of Science", "ris": "https://research.draconitic.com/paper/4fzkspfyhs5r7.ris", "sources": [ { "first_seen": "2026-11-13T12:20:02Z", "native_id": "10.1371/journal.pdig.0001827", "source": "plos", "url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001827" } ], "subjects": [ { "field": "medicine", "origin": "plos:public and occupational health", "subfield": "epidemiology-public-health" }, { "field": "medicine", "origin": "plos:nutrition", "subfield": "nutrition" } ], "title": "Prompt design in large language model health coaching chatbots: A scoping review", "title_text": "Prompt design in large language model health coaching chatbots: A scoping review", "type": "peer-reviewed", "updated_at": "2026-11-14T12:20:46Z", "url": "https://research.draconitic.com/paper/4fzkspfyhs5r7", "venue": "PLOS Digital Health", "versions": [] }