Semantic understanding, not just vectors: How Intuit’s data architecture powers agentic AI with measurable ROI
1 min read
Summary
American financial software giant Intuit is making significant strides in using Generative AI to enhance its products and services for small business customers, with an aim to improving their experience and satisfaction.
The company has deployed an agent-based AI architecture called “GenOS” that provides Generative AI capabilities to autonomously handle entire workflows and deliver quantifiable business impacts, such as quicker payment of invoices and increased likelihood of overdue invoices being paid in full.
What separates Intuit’s approach from competitors is its sophisticated data architecture designed specifically to enable agent-based AI experiences, according to CDO Ashok Srivastava.
Intuit is focusing on creating fully agentic “done for you” experiences, which handle complex, multi-step tasks while requiring only final human approval, augmenting the capabilities of its vector-based systems with a deeper, more contextual understanding of data and allowing AI agents to make more informed and meaningful decisions for customers.
This approach focuses on business outcomes rather than technological showmanship, with a goal to revolutionise the way people do business rather than just showcasing AI for its own sake.