At Myna Mahila, we harness AI and research
to develop scalable, data-backed solutions for
women's health and economic independence.

We study areas including:

Digital Health
Impact

Evaluating how digital tools enhance women’s health.

Tech Adoption
Barriers

Addressing challenges in adopting
new technologies.

Microtasking
as Employment

Understanding how task-based
work creates productive livelihoods

AI INNOVATIONS
RESEARCH

AI-powered chatbot on
WhatsApp: Myna Bolo

Myna Bolo, our groundbreaking AI chatbot, provides women with localized, quick, reliable access to health information, educational resources, and guidance on reproductive health conditions.

Built with community-driven insights and rigorous testing, Myna Bolo operates via WhatsApp, allowing intuitive interaction through text, gifs, and voice inputs.

Why Myna Bolo Matters:

Myna Bolo is trained with 170,734 real questions on sexual and reproductive health from women in the community.

Key Partner:

FEATURED

Gates Foundation Myna Mahila Foundation

How AI health care chatbots learn from…

Meet Myna Bolo, an AI chatbot that…

How AI health Care Chatbots…

AI-assisted Health
Workers: AIHW

Myna Mahila is expanding its proven training model to equip 1,500 RANI workers with AI-assisted capabilities, enhancing women’s access to reliable, community-driven healthcare guidance.

Built with generative AI and a medical feedback loop, AIHW empowers frontline health workers to dispel misconceptions, provide accurate health information, and improve healthcare access in underserved communities.

How AIHW Works:

Scalable Training: Integrates AI-powered learning into Myna Mahila’s health worker network.
Medical Oversight: Uses doctor-reviewed AI responses to ensure credibility and combat misinformation
Localized Guidance: Empowers community health workers with AI-driven tools, for accessible, actionable information.

Key Partner:

FEATURED

Data.org Announces Generative AI Skills Challenge Awardees

Pathways to Impact: Suhani Jalota

Future of Work for Women: Rani Upskilling and Work

Myna Mahila’s Rani Work model tackles systemic barriers—household responsibilities, mobility restrictions, and lack of flexible work—by leveraging AI and hyper-local solutions to create sustainable employment opportunities for women.

Our three-step approach blends technology with community-driven solutions, ensuring women can upskill, earn, and access career support:

LEARN: Digital literacy and AI training to equip women with in-demand skills.
EARN: Home-based, AI-assisted tasks through the Rani app, enabling women to participate in data annotation, AI training, and digital work.
CONNECT: Access to job counseling, peer networks, and professional development for long-term career mobility.

Progress:

Women can choose to work from home or from child-friendly Rani Centers in Mumbai, located within a five-minute walk from their homes, ensuring safe, flexible, and accessible work opportunities.

Ethical Approach with Rigorous Results

At Myna Mahila, ethics are at the core of our research and innovation.

Privacy First – We protect community data with strict security, anonymization, and responsible use.
Fair Compensation – Women’s insights matter. We pay for their time and expertise, valuing them as active contributors.
Informed Consent – Transparency at every step. No data is collected or used without clear, voluntary agreement.
Bias-Aware AI – We design inclusive, community-driven models that reflect real experiences, not just numbers.
Impact with Integrity – Our solutions are ethical, equitable, and built for lasting change.

Our research blends global expertise with a bottom-up, ethical approach that prioritizes the voices of the women we serve. We partner with institutions like Stanford University, MIT, Duke, and Emory, alongside funders such as the Bill & Melinda Gates Foundation and The Agency Fund, to deliver research that is both world-class and community-centered.

RANDOMIZED CONTROLLED TRIALS (RCTs)

Through ongoing RCTs, we’re exploring pathways to employment, emphasizing skill-building,
flexible work opportunities, and community health support systems.

A key study, the Rani RCT, a 4 year project, which involved 4,000 women, revealed:

We have other ongoing research on the field.

PUBLISHED FINDINGS

At Myna Mahila, we believe in evidence-based impact, and our work is backed by rigorous research, evaluations, and expert analysis. Below, you’ll find our working papers, peer-reviewed publications, and reports that contribute to the global conversation on women’s healthcare, economic empowerment, and digital inclusion.

Current Research:

Working Papers

Ongoing research and early findings shaping our programs

- What Works for Her?: How Remote Jobs from Home and Local Offices Affect Female Labor Force Participation in Urban India (with Lisa Ho) – Evaluating the impact of AI-assisted workforce models on women’s employment and agency.

Women’s loss in urban slums: impact of covid-19 on livelihoods, health attitudes and behaviour(Sakshi Shah, Suhani Jalota) – Women’s loss in urban slums: impact of COVID-19 on livelihoods, health attitudes and behaviour

Publications

Peer-reviewed studies contributing to academic and policy discussions

“Kya family planning after marriage hoti hai?” ( Roshini Deva, Dhruv Ramani, Tanvi Divate, Suhani Jalota, Azra Ismail) – Exploring digital interventions for improving women’s health-seeking behaviors.

Kya family planning after marriage hoti hai?”: Integrating Cultural Sensitivity in an LLM Chatbot for Reproductive Health ( Roshini Deva, Dhruv Ramani, Tanvi Divate, Suhani Jalota, Azra Ismail )

Access to sexual and reproductive health information remains a challenge in many communities globally, due to cultural taboos and limited availability of healthcare providers. Public health organizations are increasingly turning to Large Language Models (LLMs) to improve access to timely and personalized information. However, recent HCI scholarship indicates that significant challenges remain in incorporating context awareness and mitigating bias in LLMs. In this paper, we study the development of a culturally-appropriate LLM-based chatbot for reproductive health with underserved women in urban India. Through user interactions, focus groups, and interviews with multiple stakeholders, we examine the chatbot’s response to sensitive and highly contextual queries on reproductive health. Our findings reveal strengths and limitations of the system in capturing local context, and complexities around what constitutes “culture”. Finally, we discuss how local context might be better integrated, and present a framework to inform the design of culturally-sensitive chatbots for community health.
LLM Evaluation as Sociotechnical Practice: Experiences from a Research-Practice Partnership in Community Health ( Roshini Deva, Aradhana Thapa, Zeel Mehta, Shraddha Kale Kapile, Suhani Jalota, Naveena Karusala, Azra Ismail )

As large language models (LLMs) are increasingly deployed in sensitive health domains, evaluation is often framed as a technical problem of measuring accuracy, safety, or bias. Drawing on our experiences in a partnership between HCI researchers and a community health organization in India, we instead examine evaluation as an ongoing sociotechnical practice. We present a qualitative analysis of how we collaboratively developed and implemented a human-centered evaluation framework for an LLM-based sexual and reproductive health (SRH) chatbot. Through interviews with program and technical staff at the health organization, analysis of internal evaluation artifacts, and reflections from the research team, our findings show how designing and doing evaluation is shaped by organizational goals, infrastructural constraints, and the integration of diverse forms of expertise, including medical, social, cultural, and experiential knowledge. We show how research–practice stakeholders, motivated by care and responsibility towards the communities they serve, iteratively tinkered with metrics, roles, and workflows in response to tensions around medical accuracy, linguistic accessibility, cultural appropriateness, and user trust. We draw on our findings to discuss implications for taking a process-oriented approach to LLM evaluation in community health settings, and for strengthening evaluation efforts through research-practice partnerships.
Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health ( Sumon Kanti Dey, Manvi S, Zeel Mehta, Meet Shah, Unnati Agrawal, Suhani Jalota, Azra Ismail )

Large Language Models (LLMs) have been positioned as having the potential to expand access to health information in the Global South, yet their evaluation remains heavily dependent on benchmarks designed around Western norms. We present insights from a preliminary benchmarking exercise with a chatbot for sexual and reproductive health (SRH) for an underserved community in India. We evaluated using HealthBench, a benchmark for conversational health models by OpenAI. We extracted 637 SRH queries from the dataset and evaluated on the 330 single-turn conversations. Responses were evaluated using HealthBench’s rubric-based automated grader, which rated responses consistently low. However, qualitative analysis by trained annotators and public health experts revealed that many responses were actually culturally appropriate and medically accurate. We highlight recurring issues, particularly a Western bias, such as for legal framing and norms (e.g., breastfeeding in public), diet assumptions (e.g., fish safe to eat during pregnancy), and costs (e.g., insurance models). Our findings demonstrate the limitations of current benchmarks in capturing the effectiveness of systems built for different cultural and healthcare contexts. We argue for the development of culturally adaptive evaluation frameworks that meet quality standards while recognizing needs of diverse populations.
Understanding User Intent in Code-Mixed Sexual and Reproductive Health Queries in Urban India: Hierarchical Classification Approach Using Large Language Models ( Sumon Kanti Dey, Manvi S, Aradhana Thapa, Meet Shah, Zeel Mehta, Shraddha Kale Kapile, Tanvi Divate, Suhani Jalota, Azra Ismail )

Sexual and reproductive health (SRH) remains a stigmatized and taboo topic globally, limiting access to reliable information. These challenges are heightened in the Global South, where linguistic and cultural diversity further complicates information access. In India (the study context), many individuals express SRH concerns in code-mixed language, such as Hinglish (code-mixed Hindi and English), and use colloquial terms. Large language models (LLMs) could help answer SRH questions, but most are trained for English and may perform poorly on code-mixed text and miss cultural nuances. Our research aims to address this gap by assessing the current state of LLMs in understanding user intent in SRH queries for a low-resource language.

Reports & Commentaries

Insights from our fieldwork and collaborations with industry leaders

Report on Women in the Workforce: Insights from Private Companies in India(Suhani Jalota, Katherine Xu and Tanvi Divate – Key insights on integrating women into the workforce and the role of private sector engagement.

Women’s Agency in Mumbai Slums: Mitigating Biases (Priya Vishwanath) – Developing a tool to measure how labor market decisions affect women’s agency

Dignity and Agency: Empowering Women in Urban Slums Through Meaningful Work (Priya Vishwanath) – Reflecting on how dignity of women is fundamentally tied to their agency.

Ethical Approach with Rigorous Results

At Myna Mahila, ethics are at the core of our research and innovation.

Privacy First – We protect community data with strict security, anonymization, and responsible use.
Fair Compensation – Women’s insights matter. We pay for their time and expertise, valuing them as active contributors.
Informed Consent – Transparency at every step. No data is collected or used without clear, voluntary agreement.
Bias-Aware AI – We design inclusive, community-driven models that reflect real experiences, not just numbers.
Impact with Integrity – Our solutions are ethical, equitable, and built for lasting change.

Affiliated Researchers

We work closely with faculty and researchers who are interested in studying women’s agency related questions related to health, mobility, employment, and digital literacy.

Dr. Suhani Jalota

Hoover Fellow, Hoover Institution, Stanford University

Dr. Jasmin Moshfegh

Assistant Professor of Economics, Imperial College London

Dr. Azra Ismail

Assistant Professor in Biomedical Informatics and Global Health,
Emory University

Dr. Lisa Ho

Assistant Professor of Economics, Columbia University

Dr. Devansh Jalota

Assistant Professor, Industrial & Systems Engineering, Georgia Institute of Technology

Ethical Approach with Rigorous Results

At Myna Mahila, ethics are at the core of our research and innovation.

Privacy First – We protect community data with strict security, anonymization, and responsible use.
Fair Compensation – Women’s insights matter. We pay for their time and expertise, valuing them as active contributors.
Informed Consent – Transparency at every step. No data is collected or used without clear, voluntary agreement.
Informed Consent – Transparency at every step. No data is collected or used without clear, voluntary agreement.
Bias-Aware AI – We design inclusive, community-driven models that reflect real experiences, not just numbers.
Impact with Integrity – Our solutions are ethical, equitable, and built for lasting change.