PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions

TL;DR

PromptHelper is a prompt recommender system integrated into an AI chatbot that enhances user exploration and expressiveness in creative and academic writing tasks without increasing cognitive load.

Contribution

This paper introduces PromptHelper, a novel prompt recommender system that supports exploration and creativity in AI chatbot interactions, with empirical evaluation demonstrating its effectiveness.

Findings

Increases perceived exploration and expressiveness

Helps users articulate their intent more clearly

Does not increase cognitive workload

Abstract

Prompting is central to interaction with AI systems, yet many users struggle to explore alternative directions, articulate creative intent, or understand how variations in prompts shape model outputs. We introduce prompt recommender systems (PRS) as an interaction approach that supports exploration, suggesting contextually relevant follow-up prompts. We present PromptHelper, a PRS prototype integrated into an AI chatbot that surfaces semantically diverse prompt suggestions while users work on real writing tasks. We evaluate PromptHelper in a 2x2 fully within-subjects study (N=32) across creative and academic writing tasks. Results show that PromptHelper significantly increases users' perceived exploration and expressiveness without increasing cognitive workload. Qualitative findings illustrate how prompt recommendations help users branch into new directions, overcome uncertainty about what to ask next, and better articulate their intent. We discuss implications for designing AI interfaces that scaffold exploratory interaction while preserving user agency, and release open-source resources to support research on prompt recommendation.