Risk Management · Supply Chain Optimization
Dun & Bradstreet wanted to give procurement teams faster, more comprehensive supplier-risk assessments by combining its large business-data assets with conversational AI and workflow automation instead of forcing analysts through manual, time-consuming evaluations.
Reported impact
Dun & Bradstreet created a faster, more automated supplier-risk workflow that helps procurement users make better vendor decisions, anticipate supplier issues, and shorten onboarding tasks.
IBM Consulting worked with Dun & Bradstreet to create D&B Ask Procurement, an AI assistant that blends Dun & Bradstreet Data Cloud records with IBM's procurement and supplier data. The pilot runs IBM watsonx Orchestrate on IBM Cloud and uses Llama 3 and Mistral large language models to power a conversational interface for supplier-risk analysis. Watsonx Orchestrate supplies both the chat experience and the integration layer that automates repetitive procurement tasks, connects into customer systems, and lets users query large supplier datasets without manual data entry. IBM Garage methods accelerated prototyping, while IBM Expert Labs fine-tuned the AI for specific procurement workflows. The resulting architecture gives procurement users nearly instantaneous 360-degree supplier views covering financials, ownership, ESG factors, fraud potential, and revenue-based scores, plus real-time monitoring that helps them anticipate supplier issues and onboard vendors more quickly.
Supplier and procurement data from Dun & Bradstreet Data Cloud and customer systems flow into D&B Ask Procurement, watsonx Orchestrate automates retrieval and workflow steps, Llama 3 and Mistral interpret the combined data, and the assistant returns real-time supplier-risk views and onboarding guidance through a conversational interface.
D&B Ask Procurement, embedded with the integration capabilities of watsonx Orchestrate, provides the ability to query deep data on suppliers and use advanced AI technology to interpret that data.
The assistant provides a conversational chat experience that automates repetitive tasks and simplifies complex procurement processes.
The initial pilot ... integrated the advanced AI capabilities of IBM watsonx Orchestrate, Llama 3 and Mistral large language models on IBM Cloud.
estimates of 10-20% reduction in time for procurement tasks
holds over 590 million trusted and proprietary data records
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
IBM Sample Dec 10, 2025 Global Pharmaceutical Manufacturer A global pharmaceutical manufacturer needed faster, more standardized supply-chain risk analysis because manual classification, fragmented documentation, and limited visibility into alternate suppliers and materials… >1500 risk events assessed, triaged and escalated to executives as needed AWS cloud services · IBM watsonx · IBM watsonx Orchestrate 
Databricks Sample Jan 22, 2026 Dongwon Group However, their legacy data systems were siloed by business units, limiting their ability to support company-wide AI-based operations. 96% Raw material price forecasting accuracy Delta Lake · Unity Catalog 
Alibaba Cloud Sample Archived · Oct 24, 2025 ZKH As ZKH expanded, new challenges emerged, requiring swift solutions to maintain its competitive edge. To meet its high-resilience demands, the company needed a robust infrastructure capable of supporting a multi-region… By using AI to deconstruct and optimize 16 scenarios and 120 sub-scenarios, ZKH has vastly enhanced operational… Certificate Management Service · Cloud Enterprise Network (CEN) · Container Service for Kubernetes 