Natural Language Interface for Prescriptive AI Solutions in Enterprise

Abstract

Despite advancements in causal inference and prescriptive AI, its adoption in enterprise settings remains hindered primarily due to its complexity and lack of interpretability. This work at the MIT-IBM Watson AI Lab focuses on extending upon the proof-of-concept agent, PrecAIse, by designing a domain-adaptable conversational agent equipped with a suite of causal and prescriptive tools. 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 compute. We present an agent capable of function calling, maintaining faithful, interactive, and dynamic conversations, and supporting new domains.