Agentic Workflows for Conversational Human-AI Interaction Design

TL;DR

This paper introduces agentic AI workflows to improve conversational human-AI interactions by addressing ambiguity and transient engagement issues through iterative design and user testing.

Contribution

It presents a novel approach of integrating agentic AI workflows in CHAI design, supported by iterative testing and thematic analysis.

Findings

AI agents can suggest relevant prompts to clarify user goals.

Agentic workflows help simulate user interactions during early design phases.

Collaborative human-AI approaches can enhance design processes in other domains.

Abstract

Conversational human-AI interaction (CHAI) have recently driven mainstream adoption of AI. However, CHAI poses two key challenges for designers and researchers: users frequently have ambiguous goals and an incomplete understanding of AI functionalities, and the interactions are brief and transient, limiting opportunities for sustained engagement with users. AI agents can help address these challenges by suggesting contextually relevant prompts, by standing in for users during early design testing, and by helping users better articulate their goals. Guided by research-through-design, we explored agentic AI workflows through the development and testing of a probe over four iterations with 10 users. We present our findings through an annotated portfolio of design artifacts, and through thematic analysis of user experiences, offering solutions to the problems of ambiguity and transient in CHAI. Furthermore, we examine the limitations and possibilities of these AI agent workflows, suggesting that similar collaborative approaches between humans and AI could benefit other areas of design.