Through Analytics for a Better World’s 14-week Impact Accelerator Program, InfoNTD collaborated with OMP, NLR, and Sightsavers to develop an AI-powered chatbot that improves access to resources on neglected tropical diseases (NTDs). The chatbot provides frontline health workers with simple, multilingual answers and links to trusted information sources. Launched at the 2026 NNN Conference in Kigali, Rwanda, the solution demonstrates how the Accelerator helps non-profits turn real-world challenges into practical, scalable AI solutions.
Why can finding the right NTD information be difficult?
For frontline health workers, finding the right information and resources on neglected tropical diseases (NTDs) can take time, which they do not have to spare. Relevant resources are mostly spread across several websites, behind paywalls, written primarily in English or expressed in highly academic language.
To help address this challenge, InfoNTD officially launched an AI chatbot on October 1st at the 2026 NTD NGO Network (NNN) Conference in Kigali, Rwanda. Co-developed by NLR, Sightsavers, OMP and Analytics for a Better World (ABW), the tool is designed to make resources already available on InfoNTD easier to find, understand and use by frontline health workers in low- and middle-income countries.
How can AI and analytics contribute to easing healthcare delivery?
NTDs affect more than one billion people worldwide, often in settings where access to specialist health information is limited.
InfoNTD is an online platform serving as an international knowledge centre, providing access to digital information and practical tools on cross-cutting issues in NTDs. The InfoNTD platform brings together a collection of scientific publications, tools, and other relevant information to support professionals in this field; however, making these resources available is only part of the challenge.
A limited number of frontline health workers currently use the InfoNTD platform to access information and resources. However, the consortium saw an opportunity to increase their engagement by providing a faster and easier way to access these resources, resulting in the development of the InfoNTD AI-assisted chatbot.
A traditional search function requires users to choose search terms and work through the results themselves. The chatbot offers a conversational route: users can ask questions in everyday language in English, Portuguese, French, Hindi, Hausa and Amharic, receive a simple response, and follow links to the original sources on the InfoNTD platform. The chatbot is intended to help users easily navigate the knowledge base while keeping references to the source material central to the experience.
How have InfoNTD Consortium, OMP, and ABW developed the approach together?
The collaboration took shape during the first edition of ABW’s Impact Accelerator Program. The 14-week programme enables NGOs and non-profit organisations to turn significant challenges into practical AI and analytics solutions, with support from researchers, data scientists, software engineers and domain experts in ABW’s academic and industry network.
To develop a sustainable and scalable chatbot, InfoNTD joined forces with OMP, an industry leader in optimisation. OMP contributed technical development expertise, while the consortium brought its understanding of NTD information needs, the existing platform architecture, and its users.
The team developed two prototypes where they made sure that the solution centred on the needs of its users. They assessed these through user interviews, end-user surveys, and internal testing before selecting one approach for further development. Human-centric technology was the core of this solution, and the partners adapted the solution continuously as they learned more about users’ needs.
Part of the InfoNTD Consortium with the OMP team at their first in-person workshop
How did users influence the design?
Reaching frontline health workers for interviews was one of the project’s main challenges. Their time was limited, some were unfamiliar with the use of chatbots, and unreliable internet connections sometimes made conversations difficult. The team combined the interviews it could conduct with an end-user survey to better understand users’ needs.
That feedback influenced several concrete design choices. The chatbot was designed to:
use simple and accessible language
support multiple languages
ask follow-up questions when users need guidance
provide links back to the original information sources
How to build sustainable solutions?
InfoNTD also needed an approach it could sustain technically and financially. Recurring technology costs would influence how widely the chatbot could be offered and how long it could remain available, so the team considered costs and technical ownership throughout development.
The team selected Botpress, a comparatively low-cost, low-code platform that allows InfoNTD to make basic changes itself. It also coordinated with InfoNTD’s existing technology partner so the chatbot could fit into the organisation’s wider technical environment and be handed over for longer-term maintenance.
What comes next for the InfoNTD Consortium AI Assistant?
The first version focuses on cross-cutting issues relevant to multiple NTDs. In the long term, the InfoNTD Consortium aims to expand the chatbot’s knowledge base to include resources and tools relating to all neglected tropical diseases.
That expansion is currently expected to involve largely manual work. The project therefore raised a broader data question: if searching and retrieving information can be made more efficient, could parts of the process for identifying, analysing and adding new resources to the chatbot’s knowledge base also be automated? Exploring that possibility could become a follow-up project.
The launch at the NNN in Kigali connected the conference’s discussions on integration around early detection, training, and stronger health systems with a practical effort to improve access to NTD knowledge and tools. The next phase will focus on understanding whether frontline health workers find the chatbot useful, learning from how they interact with it and reaching more users while keeping recurring costs manageable. Those lessons will help shape how InfoNTD develops and maintains the tool as its coverage grows.
