Northern Trust and Microsoft deploy an AI onboarding agent that cuts data preparation time by 83%

Nov 9, 2026
Northern Trust and Microsoft deployed an AI agent that converts historical transaction data into a standard format, reducing onboarding data preparation from about two and a half weeks to three days.

Northern Trust and Microsoft announced an expanded collaboration and a new AI agent for client onboarding. The agent prepares historical investment and transaction data for clients using Northern Trust Asset Servicing's Front Office Solutions platform.

The companies said the agent reduced data preparation time by 83%, from about two and a half weeks to three days. It achieved a 96.5% F1 score on its first pass during controlled tests involving seven anonymized historical client transaction workbooks.

The agent runs on Microsoft Azure, uses Microsoft Foundry and connects with Excel and SharePoint. Northern Trust analysts can review its output, resolve exceptions and approve its work before client data enters the reporting environment. Microsoft used anonymized data to improve the system, while Northern Trust retained control of client data.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Finance AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI in Finance AI Brief AI Brief (X)
Free newsletter

Finance AI Weekly

Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets

Guide
Companies building payments for AI agents

Companies building payments for AI agents

The networks, processors, platforms, rails and startups that let AI agents pay

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.