Intro: The Core Shift

Dun & Bradstreet (D&B) has spent 180 years building the world's most comprehensive commercial database. Its Commercial Graph covers 642 million businesses, with 11,000 fields per record and 100 billion data quality checks per month. That database was designed for human analysts—credit analysts, risk managers, sales professionals—who could tolerate query latency and manually resolve ambiguous entity matches. AI agents cannot tolerate either.

When D&B's customers began deploying AI agents into credit, procurement, and supply chain workflows, the Commercial Graph became a bottleneck. The fragmented architecture, static relationship models, and human-centric query interfaces were the wrong foundation for machine consumption. So D&B rebuilt.

This is not just a technology upgrade. It is a strategic signal for every enterprise building AI agents in 2026: your data foundation is your biggest risk. D&B's rebuild reveals four structural requirements that most organizations have not yet addressed. Those who ignore them will find their agent initiatives hitting a wall—not because the AI is flawed, but because the data is not agent-native.

What Broke When Agents Started Querying

The Commercial Graph was never a single database. It was a collection of separate systems built for different use cases and markets, held together by custom integrations. Human analysts navigated that fragmentation through SQL queries or pre-built interfaces. Agents could not.

The scale of the underlying data compounded the problem. D&B's database nearly doubled in five years, from 300 million to 642 million business records. Querying that at sub-second latency against a fragmented architecture was not workable. The relationships the graph tracked were also static: a CEO linked to a company. That was the line. Agents working on credit assessments or third-party risk need dynamic relationships—when that CEO leaves for a new company, which organization does their track record follow? When a subsidiary changes ownership, how does that propagate across a corporate hierarchy? Those questions required custom analyst work before. Agents cannot wait for custom analyst work.

The broader problem is not unique to D&B. Gary Kotovets, D&B's Chief Data and Analytics Officer, told VentureBeat 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. D&B had that foundation, built over decades to serve human analysts. It still had to rebuild for agents.

What They Actually Built

The rebuild started with consolidation. D&B 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. Raw SQL access at agent query volumes and latency requirements was not the answer. Instead, D&B created a set of tools and skills available through the Model Context Protocol (MCP) that package data with context and route agents to the right records for specific queries. A match and entity resolution engine sits behind every query, confirming that when an agent asks about a company, the answer resolves to a verified, specific entity rather than a name match.

D&B Solved Agent Identity from Both Directions

Rebuilding the graph and adding MCP access solved the data retrieval problem. It did not solve the identity problem. Agents are not humans, and the authentication model built for human users did not extend to machines.

D&B built a new registration model for agents. They 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. Kotovets calls it "Know Your Agent," analogous to Know Your Customer. That handles the inbound problem: knowing which company an agent belongs to and what data it is entitled to query.

But D&B also built for the outbound problem: what happens when a customer's own multi-agent workflow loses track of which company it is analyzing. In a workflow that chains a credit check agent, a KYC agent, and a third-party risk agent, each queries D&B at a different step. Without a mechanism to confirm they are all referencing the same entity, a workflow can complete while operating on divergent records. D&B's business verification agent can be embedded into any workflow as a persistent reference point, available on Google's A2A protocol regardless of orchestration tool.

Four Strategic Requirements for Enterprise Agent Deployments

D&B's rebuild exposed four requirements that go beyond its own stack. These are structural imperatives for any enterprise deploying AI agents in 2026.

1. Data Foundations Come Before Agent Infrastructure

The CDOs and CIOs Kotovets spoke with consistently hit the same wall: they cannot build what they want in AI until their data is clean, normalized, and consolidated. D&B had that foundation already. Most enterprises do not, and they will feel it. The cost of retrofitting legacy data systems after agent deployment is exponentially higher than preparing them upfront.

2. Design for Dynamic Relationships, Not Static Ones

Enterprise data systems typically record point-in-time connections: a person belongs to a company, an asset belongs to a subsidiary. Agents working on credit, risk, or supply chain decisions need to reason across relationships that shift over time. If the underlying data only captures the static line, the agent will too. D&B rebuilt its graph to track dynamic relationships—a structural change that most enterprises have not yet contemplated.

3. Build Entity Consistency Checks into Multi-Agent Workflows

When multiple agents touch the same entity at different steps, there is no guarantee they are all referencing the same record by the time the workflow completes. That gap needs to be engineered for explicitly. Entity verification is a workflow design requirement, not an optional guardrail. D&B's verification agent acts as a "digital handshake" ensuring all agents stay aligned. Enterprises building multi-agent systems must embed similar consistency checks from day one.

4. Embed Lineage from the Start, Not as an Afterthought

Every agent-produced answer should carry a traceable path back to its source. In credit, risk, and supply chain decisions, the cost of an error is concrete. Lineage needs to be built in before scaling, not added after problems surface. D&B's system already allows users to "click and see where it came from, and validate it all the way back to the original source." That level of certainty is the key to unlocking trust in agent outputs.

Winners & Losers

Winners: Dun & Bradstreet reinforces its data moat by adapting to the AI agent era, creating new revenue streams from agent verification services. AI agent developers and enterprises gain access to verified, structured business data via standardized protocols, reducing integration friction. Google's A2A protocol gains validation as a standard for agent-to-agent communication, driving ecosystem growth.

Losers: Traditional data brokers without agent-native capabilities risk losing relevance as AI agents demand machine-readable, verified data with low latency. Companies relying on manual business verification processes will see demand shift to automated agent verification, potentially reducing their market.

Market Impact

Business verification is becoming a protocol-level service rather than a database query. D&B's move embeds trust into agent-to-agent interactions and creates a new category of 'agent identity providers.' The market for agent-native data infrastructure is set to explode as enterprises race to prepare their data foundations.

Executive Action

  • Audit your data foundation for agent-readiness: Is your data normalized, consolidated, and accessible via standardized protocols?
  • Design entity consistency checks into any multi-agent workflow you are building. Do not assume agents will stay aligned.
  • Embed data lineage from the start. In regulated industries, the cost of an untraceable agent error is existential.


Source: VentureBeat

Rate the Intelligence Signal

Intelligence FAQ

D&B's legacy database was fragmented, static, and designed for human query latency. AI agents require sub-second response, dynamic relationship tracking, and entity consistency across multi-agent workflows.

Know Your Agent is D&B's authentication model for AI agents, requiring verified IP addresses and individual access keys. It matters because it creates a trust layer for agent-to-agent transactions, which will likely become a regulatory requirement.

1) Clean, normalized data foundations before agent infrastructure. 2) Dynamic relationship models, not static ones. 3) Entity consistency checks in multi-agent workflows. 4) Embedded data lineage from the start.