ChatDify：用多智能体从自然语言自动生成 Dify 工作流
\textsc{ChatDify}: Automating End-to-End Dify Workflow Synthesis from Natural Language via Multi-Agent Collaboration
手搓 Dify 工作流太费劲的话看看这篇，ChatDify 用三个智能体把需求描述直接转成可用工作流，Qwen-3.7 后端成功率能到 0.96。
ChatDify 是一个面向 Dify 平台的多智能体框架，用 Actor-Critic 架构自动化从自然语言到完整工作流的生成。它包含三个智能体：Planner 拆解需求、Executor 做参数合成与 DSL 编译、Reviewer 负责校验与闭环修正。在 100 个模拟生产任务的基准上，配合 Qwen-3.7、GLM-5.1、DeepSeek-v4 三个后端，成功率分别达到 0.96、0.91 和 0.75。这让不熟悉 Dify 节点编排的用户也能快速搭建 LLM 应用。
\textsc{ChatDify}: Automating End-to-End Dify Workflow Synthesis from Natural Language via Multi-Agent Collaboration
The proliferation of Large Language Models has catalyzed powerful application development platforms like Dify, which enable users to build sophisticated LLM-powered workflows through modular node orchestration. However, manually configuring these workflows requires deep platform expertise and remains time-consuming and error-prone, creating a significant barrier for non-expert users. To address this challenge, we propose \textsc{ChatDify}, a novel multi-agent framework that automates end-to-end Dify workflow synthesis from natural language descriptions. \textsc{ChatDify} employs an Actor-Critic architecture comprising three specialized agents: the \textit{Planner Agent} that decomposes user requests into structured execution plans, the \textit{Executor Agent} that performs context-aware parameter synthesis and schema-augmented DSL compilation, and the \textit{Reviewer Agent} that ensures reliability through hybrid verification with closed-loop refinement. We evaluate \textsc{ChatDify} on a curated benchmark of 100 production-inspired tasks across three state-of-the-art LLM backends, achieving 0.96, 0.91, and 0.75 success rates with Qwen-3.7, GLM-5.1, and DeepSeek-v4, respectively. These results demonstrate its robustness and practical applicability for lowering the technical barrier to creating sophisticated LLM applications.