Intuit Unlocks Multi-Model AI with Breakthrough Agent System

By Netvora Tech News

---

Financial technology giant Intuit has solved a costly dilemma faced by enterprise AI teams: building sophisticated agent systems that lock them into specific large language model (LLM) vendors or constantly rewriting prompts and data pipelines as they switch between models. The company's breakthrough could reshape how organizations approach multi-model AI architectures. Like many enterprises, Intuit has built generative AI-powered solutions using multiple large language models (LLMs). Its Generative AI Operating System (GenOS) platform has been steadily advancing, providing advanced capabilities to the company's developers and end-users. GenOS has enabled agentic AI workflows that have had a measurable impact on users of Intuit's products, including QuickBooks, Credit Karma, and TurboTax. To improve productivity and overall AI efficiency, Intuit is expanding GenOS with a series of updates. The enhancements include an Agent Starter Kit that enabled 900 internal developers to build hundreds of AI agents within five weeks. The company is also debuting an "intelligent data cognition layer" that surpasses traditional retrieval-augmented generation approaches. Perhaps most impactful is that Intuit has solved one of enterprise AI's thorniest problems: building agent systems that work seamlessly across multiple large language models without forcing developers to rewrite prompts for each model. "The key problem is that when you write a prompt for one model, model A, then you tend to think about how model A is optimized, how it was built, and what you need to do when you need to switch to model B," says Ashok Srivastava, Chief Data Officer at Intuit. "The question is, do you have to rewrite it? And in the past, one would have to rewrite it."

Breaking Free from Vendor Lock-In

Intuit's breakthrough exploits genetic algorithms to eliminate vendor lock-in and reduce AI operational costs. By leveraging these algorithms, developers can build agent systems that work across multiple LLMs without rewriting prompts, significantly reducing the complexity and cost associated with multi-model AI architectures.

Beyond Retrieval-Augmented Generation: Intelligent Data Cognition

Intuit's intelligent data cognition layer is a game-changer for enterprise data. This technology enables the company's AI systems to not only retrieve and generate data but also to understand and analyze it, unlocking new insights and opportunities for data-driven decision-making.