ASAysha Shafiq
Publications / reading room2 papers

Research,
with people in mind.

How do we make AI worth trusting? Sometimes that starts with a conversation. Sometimes it starts with trying to break the code.

ACM CHI · 2026

Designing Around Stigma: Human-Centered LLMs for Menstrual Health

Human–computer interaction / health

How can a health assistant earn trust when privacy, stigma, and misinformation shape what people are willing to ask?
Conference paper
Open the paper

ACM CHI 2026 · CO-AUTHOR

Trust begins with listening.

How can a health assistant earn trust when privacy, stigma, and misinformation shape what people are willing to ask?

A two-week deployment study of an expert-grounded WhatsApp chatbot for culturally sensitive menstrual-health education, published at the top venue in human-computer interaction.

Behind the research

My contribution

I helped co-design and build the assistant, then translated what we learned in the field into concrete requirements for safer, culturally appropriate health AI.

The study

30 co-design participants · 2-week field deployment

arXiv · 2026

AI-Generated Code Reliability

Systems / software reliability

Are programs built by AI agents as reliable as release-quality human versions?
Research preprint
Open the paper

ARXIV PREPRINT · 2026

Passing tests is just the beginning.

Are programs built by AI agents as reliable as release-quality human versions?

Research supported by NSF Trusted CI studying where AI coding agents succeed and fail at reimplementing real Linux utilities from documentation alone, advised by Prof. Barton P. Miller.

Behind the research

My contribution

I designed the multi-agent methodology, built a Go-based tool to analyze source reachability through Clang, DWARF, and the linker, and rebuilt a legacy fuzzer as a concurrent, resumable, checkpointed Go tool for faster testing.

The study

10 utilities · 98% of upstream tests passed · 10× faster full-suite evaluation