AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
This addresses the challenge for non-experts in AI service design by reducing barriers through visual programming, though it appears incremental as it builds on existing no-code and natural language tools.
The paper tackled the problem of non-experts struggling to express intent and manage complexity in AI design by introducing AIAP, a no-code platform using natural language and multi-agent collaboration, resulting in a user study with 32 participants showing significant improvements in intuitive service development.
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.