✏️ CHT Community Meetup Notes

21 October 2025 Call

:globe_with_meridians: French interpretation available

Recap & Updates from Last Meeting

Topic: Exploring AI to Enhance CHT Deployments and Workflows

This community meetup featured pioneering initiatives exploring the use of Artificial Intelligence (AI) within the CHT ecosystem. The discussion highlighted the potential of AI to accelerate development, improve clinical decision support, and maintain the CHT’s core principles of being offline-first and privacy-focused.


1. CHT Multi-Agent System for Code Generation

Overview:
@hareet introduced an advanced concept for a CHT Multi-Agent System designed to move beyond single-query AI interactions. This system would use four specialized AI agents working in concert to generate high-quality, usable CHT code.

  • Research Agent: Understands previous CHT solutions, features, and validated workflows by analyzing GitHub issues and community knowledge.

  • Context Agent: Builds and maintains a growing database of what works, including pitfalls to avoid, becoming smarter over time.

  • Dev Agent: Writes the actual code, adhering to CHT code styles and best practices.

  • QA Agent: Focuses on testing, providing feedback, and ensuring code quality.

Key Benefits:

  • Standardization: Provides a community-standardized AI context and toolset, preventing individual developers from having to configure their own from scratch.

  • Flexibility: Designed to be model-agnostic, allowing the use of any LLM API (e.g., ChatGPT, Claude). This supports future efforts for data privacy and localization, including potential offline models.

  • Ecosystem Integration: The system can interact with other AI tools in the ecosystem, like the Kapa.ai docs assistant, to continuously improve its context and usefulness.

Next Steps & How to Contribute:
A forum post will be published with more detailed designs and subtasks. Community members, especially developers, are encouraged to join the upcoming working session to help divide the work and move the project forward.

Interested? Look out for the forum post and express your interest to get involved.


2. AI for Clinical Decision Support

Overview:
This project focuses on using AI to generate high-fidelity clinical applications that adhere to medical protocols. The core idea is to use AI during the setup phase to generate decision tables and forms, which are then reviewed by medical professionals and run as standard, reliable code on-device.

The Process:

  1. An LLM reviews a clinical manual (e.g., from WHO or a national ministry).

  2. It identifies gaps and edge cases (e.g., stock-outs) for medical directors to clarify.

  3. The AI breaks down the manual and generates Decision Model and Notation (DMN) tables—a format doctors can easily review and approve.

  4. These approved tables are compiled into XLSForms for deployment.

  5. The system includes extensive testing with simulated patients to validate outputs.

Key Benefits:

  • Safety & Auditability: Avoids LLM “hallucinations” at the point of care by using pre-generated, doctor-approved logic. Every decision is traceable to a source in the manual.

  • Rapid Updates: Allows for quick adaptation to new guidelines (e.g., during a pandemic) by generating new forms for review in days, not months.

  • Leverages Existing Tech: Runs on existing CHT infrastructure as standard XLSForms, making it compatible and offline-first.

Call for Collaboration:

  • Provide feedback from medical and technical staff on the approach and review artifacts.

  • Share existing hardcoded guidelines to use as a gold standard for validating the AI-generated output.

  • Participate in field testing and impact studies with Community Health Workers.

Interested? Please reach out to Professor David @David_I_Levine directly via the forum to explore collaboration. Here is a link to forum post.


Other Highlights & Resources

  • Ethical Considerations: The group discussed key factors for AI in CHT, including data privacy, security, cost, connectivity (offline capability), and accuracy.

  • Offline AI Example: A project was mentioned, which uses an offline AI model to analyze photos of rapid diagnostic tests (RDTs) and provide a result, demonstrating a practical, non-LLM application of on-device AI.

  • Existing AI Tool: The community was reminded of the Kapa.ai AI Assistant already integrated into the CHT docs site, which can answer questions in multiple languages.


Action Items & Next Steps

  1. Multi-Agent System: Look out for the upcoming forum post to join the working group.

  2. CHT-HW Project: Reach out to @David_I_Levine if your organization can provide medical/technical feedback or is interested in piloting.

A huge thank you for the insightful presentations, and to all community members for the engaging discussion. Let’s continue to explore how we can harness AI responsibly to empower health workers and strengthen health systems.

4 November 2025 Call

:globe_with_meridians: French interpretation available

Topics discussed

  • Squad updates:
    • CHW previous month performance: progressing well, there is additional work to do for the testing. @Edwin provided a demo of the feature.
    • CHT <> openIMIS interoperability: the work was already demoed in the Round Up call.
    • Hosting TCO: focused on storage reduction as a first iteration of reducing the hosting TCO. Updates to be released in 5.0 coming soon (most probably before the end of November 2025).
    • Task prioritisation: New requested functionality by MoH Kenya. User research by YUX was completed and shared in the roadmap-related ticket.
    • Upcoming:
      • CHT Custom Plugins squad
  • Feedback about current squad process
    • Having smaller groups for debugging technical issues within squads could help progress on work faster
    • Onboarding into the codebase can be challenging
  • Interest in integrating AI decision making into the task prioritisation
  • Discussion about device battery consumption

18 November 2025 Call

:globe_with_meridians: French interpretation available

Topics discussed

  • Squad updates

  • Updates from the Total Cost of Ownership squad (mainly on reducing hosting TCO)

    • The squad went through an iterative process for understanding where to make the changes that would have the most significant impact

    • Disk space is the most expensive part of running a CHT instance

    • Work with the community and partners throughout the process. Shoutout to @elijah for being a core contributor to the hosting TCO reduction work.

    • Coming in the 5.0 release - reduction in disk space up to 34%, depending on data distribution and other factors. Temporary server downtime is expected when upgrading to 5.0.

    • Hosting TCO reduction v2 coming soon!

    • Everyone is welcome to join the weekly squad calls to discuss TCO improvements and pushing next-generation functionalities into the CHT platform.

  • How often do community members use the docs site and the Ask AI widget?

    • “I use it quite a bit even just for searching for things I know are in the docs. It is good with the references“
  • When do we plan to deliver the Android notifications?

    • PRs are in review, closed to being finalized. The notifications are only for tasks at the moment.
    • Will most probably be released in CHT v5.1, and the Android wrapper will be updated too.
    • Shoutout to @jonathan @diana and @jkuester for bringing this feature to the community!