CORDIAL-AI is a UKRI-funded pilot project under the ESRC Future Data Services scheme, aiming to make complex datasets more accessible to researchers and policymakers.
It explores how advancements in large language models can enhance data services and applies this cutting-edge technology to some of the UK Data Service’s most intricate datasets.

The CORDIAL-AI prototype is currently live but not yet publicly available. Access is being provided on a limited basis. If you would like to request access to the prototype, please use the contact form to get in touch.
CORDIAL-AI explores how generative AI can help researchers and policymakers interact with complex census datasets. The project investigates methods for translating natural-language questions into structured requests, enabling reliable retrieval of tailored data while maintaining transparency and reproducibility.
The project combines large language models, specialised AI agents, and an API-driven data platform to explore new ways of retrieving structured census data. These technologies are used to test how natural-language interaction can be connected to deterministic data systems.
The project combines large language models, specialised AI agents, and a new API-driven data platform to explore new ways of retrieving structured census data. These technologies are used to test how natural-language interaction can be connected to deterministic data systems.