ASAysha Shafiq
HUMAN-CENTERED AI · FIELD STUDY

WhatsApp Menstrual Health AI

I built and field-evaluated a WhatsApp health assistant that grounds its answers in expert-curated menstrual-health content instead of model memory.

ACM CHI 2026 publication
2-week field deployment
Expert-grounded RAG
WhatsApp API · AWS · DynamoDB

Designing for a sensitive topic

Stigma, privacy, and access shape these questions, so we met people on WhatsApp rather than a new app.

Grounding over improvisation

The assistant retrieves from an expert-curated knowledge base before answering, where a hallucination would do harm.

Field evaluation

A two-week deployment was studied for trust and stigma alongside technical performance.

TextishLinux Scheduler Performance: EEVDF vs. CFSVIDER Generative Video Reconstruction