About UNFPA
UNFPA is the United Nations sexual and reproductive health agency. Our mission is to deliver a world where every pregnancy is wanted, every childbirth is safe and every young person's potential is fulfilled.Activities by UNFPA
AI-Powered Knowledge Management Search Agent
Global Not Applicable
UNFPA's AI-Powered Knowledge Management Search Agent is a secure, generative AI-driven enterprise platform trained exclusively on a ringfenced database of over 900 UNFPA programmatic evaluation reports.
Launched by UNFPA's Digital Center of Excellence, the primary objective of this tool is to faciliate access to institutional knowledge. It allows staff to query decades of dense historical programmatic data using natural language. The system utilizes Retrieval-Augmented Generation (RAG) to synthesize comprehensive answers while providing exact citations and direct links back to the specific source documents, ensuring complete factual accuracy and eliminating AI hallucinations.
This solution significantly reduces the time and resources required for staff to conduct desk reviews, background research, and strategic planning. By instantly surfacing validated, historical insights from past interventions, the agent ensures that future UNFPA programming and policy decisions are firmly grounded in robust evidence, all while keeping institutional data strictly within a secure, controlled IT environment.
Gender Bias Overview Tool (GenBOT)
Global United States
The Gender Bias Overview Tool (GenBOT) project involved a partnership among UNICC, UNFPA, and Columbia University Capstone participants from 2024. Gender bias in datasets, particularly in the field of machine learning and AI, has been a long-standing issue. Despite efforts toward inclusivity and diversity, women remain underrepresented in various stages of tech development, leading to inherent biases in datasets. These biases perpetuate themselves in the development of machine learning models and algorithms, causing skewed or inaccurate outputs that reinforce existing gender disparities. To address this issue, UNICC collaborated with UNFPA and Columbia University (students and faculty) to develop GenBOT, an adaptable data-auditing solution that provides users insights on gender bias in their datasets through automated AI analytics. The tool aims to guide stakeholders in creating equitable, gender-inclusive technologies and services.
Context Matters: A key lesson learned was the importance of context in evaluating gender bias. The definition and scope of bias need to be carefully defined with stakeholders to ensure the tool's effectiveness. Thresholds and Metrics: Determining appropriate thresholds for gender bias detection was a significant challenge. The team used established research and studies to refine the metrics used in the tool, ensuring that they aligned with best practices. Stakeholder Collaboration: Continuous communication with stakeholders such as UNFPA and UNICC was crucial in refining the bias thresholds and understanding their specific needs for gender bias detection.
ECHO: Amplifying citizen’s voices for the SDGs
Latin America and the Caribbean ColombiaECHO is an AI-powered tool that promotes citizens’ participatory planning and awareness about the SDGs through real-time guided public discussion. It uses Automatic Speech Recognition, Cognitive Computing, and Data Analytics to process large amounts of information from individuals, including minorities and vulnerable populations.
Activity Type AI Tools/SolutionsResearch/Reports/AssessmentsAwareness/AdvocacyGenerative AI-Powered Evaluation Assistant
Global Not Applicable
The Generative AI-Powered Evaluation Assistant is a strategic initiative by UNFPA's Independent Evaluation Office (IEO) to streamline UNFPA’s evaluation processes.
Using secure enterprise tools like Google Vertex AI and Gemini, the IEO has developed a custom AI application that automatically discovers, analyzes, and summarizes massive amounts of institutional evaluation data. It performs multi-level synthesis across global, regional, and country-level reports to generate comprehensive evidence briefings, coverage reports, and gap maps.