D&B's database of 642 million businesses was built for humans, not AI agents. So they rebuilt it.

Dun & Bradstreet has spent over 180 years constructing a vast commercial database. Its Commercial Graph, which covers 642 million businesses and their relationships, corporate hierarchies, and risk profiles, was originally designed for human analysts. Credit analysts, risk managers, and sales professionals could wait for query results and work through ambiguous entity matches.

However, AI agents cannot operate in the same way. When D&B's customers began integrating agents into their credit, procurement, and supply chain workflows, the Commercial Graph that had reliably served nearly 200,000 customers globally became a problem. The systems built to serve human analysts had the wrong architecture for machines.

So, D&B rebuilt its database. "We need to think about agents as our new consumer category, evolving from our standard credit analysts or sales and marketing professionals, et cetera, to also now catering to these customers' agents," Gary Kotovets, Chief Data and Analytics Officer at Dun & Bradstreet, told VentureBeat. The original Commercial Graph was a collection of separate systems built for different use cases and markets, held together by custom integrations.

Human analysts could navigate this fragmentation through SQL queries or pre-built interfaces, but AI agents could not. The scale of the underlying data compounded the problem. The database had nearly doubled in five years, expanding from more than 300 million to more than 642 million business records, with 11,000 fields per record.

The firm now runs approximately 100 billion data quality checks per month as records move through its systems. D&B's rebuild started with consolidation. The company migrated its fragmented databases to cloud infrastructure, redesigned the underlying schema, and built a data fabric layer that normalizes records across markets while preserving regional compliance requirements.

The result is a unified knowledge graph that tracks billions of relationships across 642 million companies, continuously updated and enriched by AI-driven data processing. On top of that graph, D&B built a structured access layer for agents, complete with a match and entity resolution engine that confirms the identity of the queried entity. The rebuild also required a new registration model for agents, which must map to a verified IP address and register an individual access key, treated as an authenticated identity in the same pipeline as a human user.

D&B solved the identity problem from both directions, handling the inbound issue of knowing which company an agent belongs to and what data it is entitled to query, as well as the outbound issue of ensuring that workflows referencing the same entity are using the correct data. The broader problem is not unique to D&B. Kotovets said he has spoken with hundreds of CDOs and CIOs over the past six months and consistently heard the same constraint: they could not build what they wanted in AI because their data foundations were not standardized, normalized, or agent-queryable.