Domain Adaptable Prescriptive AI Agent for Enterprise

TL;DR

This paper introduces PrecAIse, a domain-adaptable conversational AI agent that simplifies access to advanced causal inference and prescriptive analytics for enterprise users through natural language interfaces.

Contribution

It presents a novel, domain-adaptable conversational agent with a natural language interface that makes complex causal and prescriptive tools accessible to non-expert enterprise users.

Findings

Developed PrecAIse, a proof-of-concept conversational agent.

Enabled users to perform causal inference and prescriptive analytics via natural language.

Supported multi-domain, interactive, and dynamic conversations.

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.