AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration

2025-08-04

AI Summary

Non-expert users face dual challenges in AI service design: ambiguous intent expression and high system complexity. To address these, we propose a natural language–driven, visual, no-code AI workflow platform that innovatively integrates multi-agent collaboration with natural language processing (NLP). The platform automatically parses and decomposes user-provided ambiguous instructions into executable, modular components, enabling end-to-end development via visual workflow orchestration. By abstracting away low-level technical details, it establishes an automated “semantic–action–data” recognition and mapping mechanism, substantially lowering the barrier to AI service creation. A user study (N=32) demonstrates that, compared to conventional tools, our platform improves development efficiency by 47%, increases task completion rate by 39%, and achieves significantly higher intuitiveness scores. These results empirically validate the effectiveness and feasibility of natural language–enhanced visual programming for democratizing AI.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Intelligent User Interfaces
• Computer Vision: Language and Vision

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Enables non-experts to design AI without coding
• Simplifies complex system management via natural language
• Improves intuitive service development with AI suggestions

Innovation

• No-code platform with natural language input
• Multi-agent system decomposes user instructions
• AI-generated suggestions improve workflow design