During the first edition of the Impact Accelerator Program, the InfoNTD Consortium and OMP and Analytics for a Better World co-developed an AI chatbot to make technical information on neglected tropical diseases easier for frontline health workers and researchers to find and use. The first version focuses on cross-cutting NTD topics, with the longer-term ambition of extending the tool across all 21 neglected tropical diseases.
Why can finding the right NTD information be difficult?
The InfoNTD Consortium brings together knowledge and tools on neglected tropical diseases, or NTDs — a group of diseases that affect more than one billion people worldwide and often occur in settings where access to specialist health information can be limited.
InfoNTD is an online platform serving as an international knowledge centre, providing access to digital information resources on cross-cutting issues in neglected tropical diseases (NTDs). The InfoNTD Consortium brings together a comprehensive collection of scientific publications, tools, and resources to support professionals in this field, but making resources available is only part of the challenge.
For frontline health workers and researchers, having information available does not automatically mean it is easy to use. Relevant guidance may be spread across many resources, written primarily in English or expressed in highly academic language.
To help address this challenge, InfoNTD officially launched the InfoNTD AI Assistant on October 1st at the 2026 NNN Conference in Kigali. Co-developed with OMP and Analytics for a Better World (ABW), the tool is designed to make the consortium’s existing knowledge easier to find, understand and use by frontline health professionals.
How can AI and analytics contribute to easing healthcare delivery?
Frontline health workers often need practical, reliable NTD information most urgently, yet they face some of the greatest barriers to accessing it. Limited time, language barriers, varying familiarity with academic search methods, and the challenge of translating a practical question into effective search terms make it difficult to navigate a large knowledge repository. As a result, InfoNTD’s existing keyword-based platform has not always been able to serve frontline users as directly and efficiently as needed, despite the relevance of its resources to their day-to-day work. The consortium therefore sought to make this knowledge easier to access in ways that better reflect how frontline health workers look for and use information in practice.
A traditional search function requires users to identify appropriate search terms, review multiple results, and determine which resources are most relevant to their context. The chatbot provides a more direct, conversational route. Users can ask questions in everyday language in English, Portuguese, French, Hindi, Hausa, and Amharic, receive a focused response, and follow links to the original sources. Rather than replacing expert guidance or the underlying evidence base, it supports users in navigating InfoNTD’s knowledge more efficiently, lowering barriers to finding relevant information while keeping trusted 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 InfoNTD, and unreliable internet connections sometimes made conversations difficult.
Rather than designing around assumptions, the team combined the interviews they could conduct with an end-user survey.
That feedback influenced several concrete design choices. The chatbot was designed to:
use simple and accessible language
offer multilingual support
ask follow-up questions when users need guidance
provide links back to the original information sources
The project also changed direction as evidence emerged. The partners did not follow a fixed development plan; they adapted the solution as prototypes, interviews and testing showed what users needed. These choices were intended to make the tool easier to use across different contexts rather than expecting users to adapt to a technically complex interface.
How to build sustainable solutions?
Building a chatbot was only useful if InfoNTD can maintain it after the accelerator programme ended. For that reason, the team considered operating costs and technical ownership during development rather than after the tool had been built.
Recurring technology costs could affect how widely and for how long the chatbot can be made available. That consideration influenced the decision to use a comparatively low-cost platform from the beginning. They selected Botpress, a low-code platform, so that the InfoNTD team can independently sustain the needed changes internally and so that the solution 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 longer term, the InfoNTD Consortium aims to expand the chatbot’s knowledge base to include resources and tools relating to all 21 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 in Kigali connected the conference’s discussions on early detection, training and stronger health systems with a practical effort to improve access to NTD knowledge. 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.
