Global Stakeholder Meeting

​

5^th March 2026

funded by

Agenda

• Brief project overview
• Outline of end-user profiles
• Initial prototype for the output report
• Discussion on output prototype, data sources and other considerations
• Continued engagement and future meetings

​

Use of meeting data

• We will audio record and transcribe the meeting, to understand how to improve our designs
• We will not disclose identifiable information about any points you make
• If, later, you don’t wish your feedback to be analysed, please contact us to remove your contributions

​

Solace-AI Background

• 5-year grant from April 2025 under the Wellcome Trust call for “Advancing Evidence Synthesis for Climate and Health”

​

​

• Extreme events and climate change related emergencies will increase in frequency and intensity with far reaching health impacts

​

• Preparing for, responding to and developing adaptation actions requires accurate and rapid evidence to inform decisions and policies

​

• Traditional evidence synthesis methods are too slow, require too many resources, do not always take issues of health equity or local contexts into account, usually do not capture information from so-called grey literature

​

What is Solace-AI?

• Synthesizing Online Literature on Adaptation to Climate Emergencies

​

• Scientifically sound AI system that will generate rapid, real-time evidence to support policy and humanitarian response to climate related health emergencies

​

• Will draw on scientific literature, case studies, grey literature to synthesize accurate and context-specific summaries for policy makers, health and humanitarian workers

​

​

What is Solace-AI?

• Solace-AI synthesis can drastically reduce time, effort and cost of evidence synthesis

​

• Evidence will be on-demand and up-to-date

​

• Has the potential to address climate-health issues, countries, and health-equity issues that are often ignored

​

• Contribute to better, evidence informed decision making and improve the lives of affected communities

​

Problems with existing “deep research” systems

Black box methods

Trust

Case study 1: Climate change and mental health in Ethiopia

Ethiopia, September 2025

• The Solace-AI team met with key stakeholders in Addis Ababa, Ethiopia as part of the co-design process for the 1^st case study

​

• The stakeholders included government officials (including the State minister of health), NGO and WHO officials, regional disaster risk reduction authority officials, and academics

​

• The team travelled to the Somali region to visit the Qoloji camp for internally displaced people to understand local experiences with climate related disasters and their health impacts

​

• Further work ongoing to see how Solace-AI can be a tool to address the mental health impacts of climate change in the Somali region.

​

​

End-user Personas - Who will use Solace-AI?

Initial prototype for output report

Initial output prototype: Examples

Initial output prototype: Framework

Initial output prototype: Overview

​

• Intended to be the main page with the most key information on the question asked, the main synthesized evidence with its strength

​

• Will include date of generation

​

• Will include information on the types of sources

​

• Will have option to read the “full report”

Initial output prototype: Full Report

​

​

​

• Background with details on the burden of disease, latest information based on the question (health and/or climate)

​

• If the question is asked for a specific region, synthesis of relevant evidence from that region or similar contexts. Where evidence is sparse, will have global evidence

​

• Evidence-based recommendations for the best interventions, implementation strategies, etc depending on the question asked

​

• Other considerations relevant to the question (e.g. for cholera outbreaks, considering improving community education and awareness on hygiene and sanitation along with vaccinations)

​

• Will include all sources and methods used

Discussion

Discussion on the output report

​

Reflections on…

The structure of the output report

The content of the output report

How the output report could be used

Reflections on structure

Is the structure clear and intuitive?

Could any sections be reordered?

How easy is it to navigate the report?

How could we improve the structure to increase accessibility?

Reflections on content

Are the key messages clear and appropriate?

Is there anything missing that you would like to see?

Does the level of detail feel appropriate?

How accessible is the language and tone?

Are the evidence sources clear and appropriate?

Are there any particular evidence repositories that we should add?

​

Reflections on use

How, if at all, could you use the report in your own work?

How, if at all, could the report inform decision making?

What are the most useful features of the report?

Could we add or change anything to make the report more useful?

​

​

THANK YOU!

​

Global Stakeholder Meeting

​

5^th March 2026

​

Website: www.solaceai.org

PI Contact: iain.marshall@kcl.ac.uk

funded by

Tentative case study examples

Ethiopia: Addressing poor mental health and substance misuse in displaced communities

Somalia/Somaliland: Climate change related anthrax risk

India: Cardiovascular impacts of extreme heat in vulnerable populations

South Africa: Managing cholera risk after flooding

Scotland: Managing impacts of climate change on respiratory disease

Global/MSF: Responding to arbovirus outbreaks

Participatory approach and role of stakeholders

Participation in co-creation

• Advising and providing critical oversight of project
• Informing methods
• Informing evaluation and system design (including user interface, etc)
• Providing expertise, technical, and local knowledge

​

Contribute to defining case studies

• Based on urgent problems faced by regions or communities
• Case studies will provide focus for the design and real-world evaluation of SOLACE-AI

​

Regular engagement

• Through emails, periodic online meetings, workshops (where feasible)
• We will use participatory approaches eg storyboarding, and low-fidelity prototypes to co-design the system

​

​