BRI DataLab: an AI-assisted research platform for Chinese infrastructure finance

BRI DataLab is an open-source web platform that integrates a harmonized infrastructure financing dataset, a curated policy and academic document corpus, and a retrieval-augmented generation (RAG) interface into a single queryable research environment for Chinese overseas development finance. Analysts working on the Belt and Road Initiative (BRI) must move between datasets, government documents, and academic literature without an integrated interface for querying across all three at once. This paper documents BRI DataLab, a research platform that combines a harmonized project-level dataset derived from AidData's China's Global Loans and Grants Dataset v1.0 with a curated corpus of 42 policy documents, institutional reports, and academic sources, accessed through an AI-assisted retrieval and synthesis layer built on RAG. Three methodological contributions are described: the decisions involved in converting more than 33,000 tranche-level financing records into 4,861 infrastructure projects; the four-category selection framework governing the document collection; and the system design of the AI interface, including the epistemic constraints built into its system prompt. The central argument is that AI-assisted research interfaces are methodologically defensible when they are transparent about what they can and cannot establish.