evidoria

← Back to browse

Good practice Imported

Sakhi — AI Menstrual-Health Chatbot Keeping Bangladeshi Girls in School

Bangladesh · Dhaka · See the Bangladesh profile · See the Dhaka profile

Evidence: Descriptive / self-reported Top 73% 40/100 · Ask Evidence Copilot about this practice

SimPPL's WhatsApp chatbot delivers AI-generated, stigma-free menstrual-health guidance in Bangla to young girls in Dhaka, targeting the absenteeism menstruation causes for roughly 1 in 10 adolescent girls across the region, per UNESCO estimates.

200+ across 6 public health centres
Users, Spreeha Foundation pilot
100+ young girls
Reach, Asian University for Women Marma pilot
15% target, within a year
Target awareness gain, rural areas

Details

Maturity
Pilot
Promoter
SimPPL (with Spreeha Foundation and Asian University for Women)
Period
2023–2025 (pilot, ongoing)
Keywords
public health, menstrual health, WhatsApp chatbot, nonprofit research

Context

Sakhi is a multilingual AI chatbot built by nonprofit research collective SimPPL that delivers verified, judgment-free menstrual-health information over WhatsApp in Bangla and English, targeting a UNESCO-estimated gap where roughly 1 in 10 adolescent girls in the region miss school during menstruation.

Results

Sakhi has been piloted with the Spreeha Foundation across six public health centres around Dhaka (200+ users) and with the Asian University for Women in a Marma community pilot reaching 100+ young girls. The team tracks impact through pre/post-treatment surveys and in-app engagement metrics, targeting a 15% awareness gain in rural areas and 25% in urban areas within a year.

Conclusions

Sakhi was selected as a solution in MIT Solve's 2024 Global Health Challenge, but as a nine-month-old pilot funded by a single MIT PKG IDEAS grant it has not yet published outcome results, and no public data-protection policy for this health chatbot serving minors was found.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
SimPPL research team, Spreeha Foundation health-centre staff

Conditions for success

  • Low-friction delivery over an existing messaging platform (WhatsApp)
  • Partnership with a local health foundation and university

Common failure modes

  • No published outcome results yet against stated awareness-gain targets
  • No public data-protection policy found for a chatbot serving minors on health topics

Commonly funded by

Philanthropic / foundation funding

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful