Northern Trust and Microsoft deploy AI agent for client onboarding
Northern Trust and Microsoft are deploying an AI-powered client onboarding agent for clients using Northern Trust Asset Servicing’s Front Office Solutions platform. The companies say the tool cuts data preparation time by 83%, from two and a half weeks to three days, while retaining analyst oversight and financial services controls.
- The AI agent serves clients on Northern Trust’s Front Office Solutions platform.
- Northern Trust says preparation time fell 83%, from two and a half weeks to three days.
- Controlled testing produced a 96.5% F1 first-pass quality score.
- Analysts review outputs, handle exceptions and approve the agent’s work.
- The agent is built on Microsoft Azure and uses Microsoft Foundry.
AI converts historical investment data
Announced on Nov. 9, 2026, the expanded collaboration brings together Northern Trust and Microsoft Corp., including Microsoft Frontier Company Forward Deployed Engineering teams. The jointly developed agent addresses a complex stage of institutional onboarding: converting years of investment and transaction history from multiple sources into a standardized format for Northern Trust’s reporting environment.
Front Office Solutions provides performance and analytics for institutional investors, including foundations, endowments, pension schemes and large family offices. Onboarding these clients can involve reconstructing performance histories from large volumes of data, especially for alternative assets.
According to Northern Trust, the agent reduced data preparation time by 83% in real client onboarding scenarios, from approximately two and a half weeks to three days. In controlled testing across seven representative test cases using real, anonymized historical client transaction workbooks, the system achieved a 96.5% F1 first-pass quality score. F1 combines precision and recall into a single quality metric.
Human review remains part of the workflow
The system is designed to support analysts rather than remove them from the process. Analysts can review outputs, assess the agent’s reasoning, resolve exceptions and provide feedback to improve performance. They can also identify and reconcile errors before a client goes live, while validating the client’s starting data.
Built on Microsoft Azure, the agent uses Microsoft Foundry for enterprise AI and connects with Microsoft Excel and SharePoint. These tools allow Northern Trust analysts to review, refine and approve the agent’s work. A governed intelligence layer preserves approved onboarding knowledge, enabling the solution to build on institutional expertise over time.
Northern Trust said privacy, security and governance controls were central to development. Microsoft evaluated F1 first-pass quality and other measurements using anonymized data, while Northern Trust client data remained under the firm’s control. The companies said this approach supported production-scale performance and the data stewardship requirements of a regulated industry.
A regulated-industry test for enterprise AI
The companies’ announcement reflects a wider data challenge in asset management. Northern Trust said 57% of surveyed asset owners identified the consolidation of data from multiple, disparate internal and external sources as their biggest challenge.
Pete Cherecwich, Chief Operating Officer at Northern Trust, said the agent combines the company’s asset servicing expertise with Microsoft’s AI capabilities and reduces the time needed to prepare and validate client data. “The solution reduces the time required to prepare and validate clients’ data while maintaining the oversight and controls our clients expect, creating capacity for both sides to focus on higher-value work,” he said.
Bill Borden, Corporate Vice President, Worldwide Financial Services at Microsoft, said the collaboration demonstrates how AI can amplify human expertise in regulated industries. For users, the immediate effect described by the companies is a faster and more predictable onboarding process, with analysts retaining responsibility for review, exception handling and approval. For the market, the project offers an example of deploying AI in a sensitive operational workflow while keeping data ownership, governance and institutional knowledge with the financial institution.
