Parenting Journal · Volume 1 · Issue 2 · Licensed source edition
Designing Rosie the Chatbot with and for Pregnant and New Mothers of Color: a Community-Engaged Study Leveraging Artificial Intelligence and Prevention Science to Improve Maternal and Child Health Outcomes
Originally published 2026-04-17 · Prevention Science
Springer Science and Business Media LLC · DOI 10.1007/s11121-026-01901-7 ↗
AI / system type
Generative AI/LLM; retrieval-grounded LLaMA chatbot
Direct parenting evidenceDirectly addresses parents or caregiving, including parent studies, syntheses and audits of parenting advice.
The AI connection
Rosie combines retriever, reranker and LLaMA reader grounded in a vetted corpus.
Why this reading matters
Centers underrepresented mothers as design contributors rather than merely end users.
Editorial reading guide · Collaboration
How can parents help design an AI tool that understands their community’s needs?
Maps to Collaboration by involving intended users in shaping culturally relevant maternal/infant AI information.
Study context
30 pregnant/new mothers of color in six US virtual focus groups
Age / stage: Pregnancy and infant age under 6 months; mothers 17–39
Read with three questions
- Which health-information needs did mothers prioritize?
- How did preferred support sources inform chatbot design?
- How does Rosie’s vetted retrieval pipeline constrain responses?
Keep the limits in view
Early prototype and mostly college-educated online-recruited sample; preferences do not demonstrate clinical effectiveness or representative needs of all mothers of color.
The text below is the original article’s licensed repository edition. Its wording is not rewritten. Use the Paper Agent beside the text to locate evidence; open the source for figures, tables and complete context.
Opening the verified paper and agent…
Checking the article identity, license record, and saved source text.
Open the repository recordAttribution & reuse
Follow the original.
Original authorship, publication date, journal and DOI are preserved. This issue’s TRICK placement and reading questions are editorial additions, not claims made by the original authors.
Elizabeth M Norell; Amara Channell Doig; Michelle Jasczynski; Alexis S Hunter; Francia Ximena Marin Gutierrez; Heran Mane; Sourabh Mane; Xiaohe Yue; Quynh C Nguyen (2026). Designing Rosie the Chatbot with and for Pregnant and New Mothers of Color: a Community-Engaged Study Leveraging Artificial Intelligence and Prevention Science to Improve Maternal and Child Health Outcomes Prevention Science. https://doi.org/10.1007/s11121-026-01901-7
Permissions checked against the saved article notice; repository publication notices screened 2026-11-04. This is not a new peer-review decision. The source authors and publishers are not represented as endorsing this issue.