Wordflow: Social Prompt Engineering for Large Language Models

crown jewel figure
Wordflow is an open-source social prompt engineering tool to help everyday users create, run, share, and discover prompts for large language models (LLMs). (A) The Editor View offers an easy-to-use text editing interface, allowing users to run an LLM prompt using the selected text as input by simply clicking on a button and examine the changes made by LLMs. (B) The Prompt Manager enables users to edit and curate prompts, adjust LLM settings, and share their prompts with the community.
Demo Video
Large language models (LLMs) require well-crafted prompts for effective use. Prompt engineering, the process of designing prompts, is challenging, particularly for non-experts who are less familiar with AI technologies. While researchers have proposed techniques and tools to assist LLM users in prompt design, these works primarily target AI application developers rather than non-experts. To address this research gap, we propose social prompt engineering, a novel paradigm that leverages social computing techniques to facilitate collaborative prompt design. To investigate social prompt engineering, we introduce Wordflow, an open-source and social text editor that enables everyday users to easily create, run, share, and discover LLM prompts. Additionally, by leveraging modern web technologies, Wordflow allows users to run LLMs locally and privately in their browsers. Two usage scenarios highlight how social prompt engineering and our tool can enhance laypeople's interaction with LLMs. Wordflow is publicly accessible at https://poloclub.github.io/wordflow.
Wordflow: Social Prompt Engineering for Large Language Models
  title = {Wordflow: {{Social Prompt Engineering}} for {{Large Language Models}}},
  shorttitle = {Wordflow},
  author = {Wang, Zijie J. and Chakravarthy, Aishwarya and Munechika, David and Chau, Duen Horng},
  year = {2024},
  url = {http://arxiv.org/abs/2401.14447},
  urldate = {2024-01-29},
  archiveprefix = {arxiv},
  journal = {arXiv 2401.14447}