Pregnant women struggle for answers

Zimbabwe's public health services are stretched thin, leaving pregnant women unable to access reliable information about pregnancy and childbirth from overworked midwives.

Samantha's search for information

Harare resident Samantha Murungweni, twenty-five, registered for antenatal care but could not ask midwives all her questions. She turned to friends and social media for answers.

DawaMom enters the picture

A friend introduced Murungweni to DawaMom, an AI-powered chatbot designed to provide pregnancy-related information. She started using it in her second trimester.

“I asked about food that would keep both of us healthy. I also asked about back pain, frequent urination and foetus movements in the uterus. It felt like I was talking to a real midwife.”

DawaHealth's WhatsApp strategy

Developed in twenty twenty-four by DawaHealth, a Zambia-based startup, DawaMom gives pregnant women validated medical information via WhatsApp. Accessing the chatbot is free, but advanced services require a subscription.

“Google is not accessible to everyone because internet data is expensive, but most people still keep a WhatsApp data bundle.”

Building a verified knowledge base

DawaMom uses retrieval-augmented generation to provide answers from a verified database compiled from Health Ministry guidelines, World Health Organization recommendations, medical school curricula and hospital protocols.

“More than twenty-five health workers translated and validated this content into Shona, Ndebele and Tonga. Every answer DawaMom gives is drawn from this database.”

Speaking users' language

DawaHealth worked with more than thirty women to build an English-Shona code-switching dataset so DawaMom understands how people actually speak and replies in a natural Shona accent.

Zimbabwe's health worker shortage

Zimbabwe had just over twenty-two health workers per ten thousand people in twenty twenty-two, less than half the World Health Organization's recommended forty-five per ten thousand.

AI as a force multiplier

Elijah Dakwa, president of the Zimbabwe Medical Analytics and Informatics Network, says AI can help if used to support health workers, not replace them, enabling clinicians to focus on high-risk cases.

“When that is in place, AI acts as a force multiplier: faster, more consistent, clearer decision-support systems for health workers and fewer unnecessary trips to central hospitals.”

Identifying high-risk pregnancies saves lives

DawaMom identifies women needing urgent follow-up and those who can be reassured at home. Rutendo from Rusape consulted the chatbot about lack of foetal movement and was advised to see a doctor immediately.

“The information I got saved my life.”