AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
Abstract
While many tools are available for designing AI, non-experts still face challenges in clearly expressing their intent and managing system complexity. We introduce AIAP, a no-code platform that integrates natural language input with visual workflows. AIAP leverages a coordinated multi-agent system to decompose ambiguous user instructions into modular, actionable steps, hidden from users behind a unified interface. A user study involving 32 participants showed that AIAP's AI-generated suggestions, modular workflows, and automatic identification of data, actions, and context significantly improved participants' ability to develop services intuitively. These findings highlight that natural language-based visual programming significantly reduces barriers and enhances user experience in AI service design.
Cite
@article{arxiv.2508.02470,
title = {AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration},
author = {Hyunjn An and Yongwon Kim and Wonduk Seo and Joonil Park and Daye Kang and Changhoon Oh and Dokyun Kim and Seunghyun Lee},
journal= {arXiv preprint arXiv:2508.02470},
year = {2025}
}
Comments
14 pages, 6 figures