AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909720857542656 |
|---|---|
| author | An, Hyunjn Kim, Yongwon Seo, Wonduk Park, Joonil Kang, Daye Oh, Changhoon Kim, Dokyun Lee, Seunghyun |
| author_facet | An, Hyunjn Kim, Yongwon Seo, Wonduk Park, Joonil Kang, Daye Oh, Changhoon Kim, Dokyun Lee, Seunghyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration An, Hyunjn Kim, Yongwon Seo, Wonduk Park, Joonil Kang, Daye Oh, Changhoon Kim, Dokyun Lee, Seunghyun Human-Computer Interaction Artificial Intelligence Computation and Language Multiagent Systems Software Engineering 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. |
| title | AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language Multiagent Systems Software Engineering |
| url | https://arxiv.org/abs/2508.02470 |