A Conversational Assistant Framework for Automation

This paper describes the design and implementation of an AI-enabled conversational assistant to enhance the efficacy of Business Process Automation (BPA) tools in the context of IBM's watsonx Orchestrate platform. It leverages the capabilities of large language models (LLMs) to interpret natural language instructions and unstructured documents, thereby simplifying the workflow development process. We detail the assistant framework's architecture, which supports extendable, event-driven interactions and dynamically integrates multiple agents. We demonstrate its utility through a real sales prospecting use case, which showcases its ability to facilitate the authoring of workflows, decision rules, and data models. Additionally, our empirical evaluation demonstrates the accuracy of routing user requests, efficacy in workflow authoring, and the precision of API field mapping recommendations.