Domain Adaptable Prescriptive AI Agent for Enterprise
Piero Orderique, Wei Sun, Kristjan Greenewald
TL;DR
This work addresses the gap between advanced prescriptive AI methods and enterprise usability by introducing PrecAIse, a domain-adaptable NLUI that enables non-experts to access causal inference and prescriptive analytics via natural language. It proposes an automated generalization pipeline that auto-generates domain-specific components from a dataset, and uses prompt tuning, memory, and thought-injection to improve reliability and reduce hallucinations. The system combines function calling with a conversational interface and multimodal outputs, validated by quantitative gains in intent recognition and parameter extraction, as well as qualitative improvements in dialogue naturalness. The approach promises scalable, two-way, explainable domain adaptation for enterprise decision-making with minimal manual effort and compute time.
Abstract
Despite advancements in causal inference and prescriptive AI, its adoption in enterprise settings remains hindered primarily due to its technical complexity. Many users lack the necessary knowledge and appropriate tools to effectively leverage these technologies. This work at the MIT-IBM Watson AI Lab focuses on developing the proof-of-concept agent, PrecAIse, a domain-adaptable conversational agent equipped with a suite of causal and prescriptive tools to help enterprise users make better business decisions. The objective is to make advanced, novel causal inference and prescriptive tools widely accessible through natural language interactions. The presented Natural Language User Interface (NLUI) enables users with limited expertise in machine learning and data science to harness prescriptive analytics in their decision-making processes without requiring intensive computing resources. We present an agent capable of function calling, maintaining faithful, interactive, and dynamic conversations, and supporting new domains.