From Natural Language to Workflows: Towards Emergent Intelligence in Robotic Process Automation

RPA technologies allow the automation of repeated processes through indirect or direct instruction from the end-user. While declarative authoring techniques provide a powerful tool to scale up process complexity with RPA elements, often such techniques are difficult to use without expertise. In this work, we will explore systems (in the context of web service composition and goal-oriented conversational agents) that both consumers and developers can interact with, in natural language, to compose RPA elements that demonstrate emergent intelligence as a composition of smaller units of automation. We will also discuss the overhead in authoring such systems, and potential learning opportunities in reducing said overhead. Finally, we will explore issues of explainability for the developer and transparency of dynamic compositions for the consumer in dealing with such systems with aggregated automation.