UN and Google Build Data Platform for AI Systems

The United Nations is working with Google to make its global statistics easier for AI systems to access. The UN System Data Commons, built on Google’s open-source Data Commons, lets users search data from UN agencies with natural-language queries. It replaces UNData and supports the Model Context Protocol (MCP), which connects AI systems to external sources.

The project follows a UNICEF working paper that tested six AI models across more than 133,000 responses about global development indicators. The models achieved an average accuracy score of 21.2%. About three in five responses did not provide a usable number. When the questions were repeated on the same model versions about two days later, models that gave a number both times returned the same number only about half the time.

The study has not been peer-reviewed. UNICEF plans to release its methodology, code, and data with the paper. The UN said 26 entities have committed to the platform, with data from nearly 20 available at launch, and it aims to add 80% of the UN system’s statistical datasets by 2027.

Google.org provided $2 million in funding and technical support. Google launched Data Commons in 2018. The UN platform records each statistic’s source, while MCP can help AI systems combine indicators into dashboards and analysis. Google’s Prem Ramaswamy said people should review AI outputs because models can misinterpret nuance.