让AI写代码不再是一次性脚本：可编辑的数据管道来了
现在的AI写代码助手（比如Claude Code）能帮你生成数据处理脚本，但脚本跑完就没了，想改得重来。这篇论文做了一个平台，让AI直接生成可拖拽、可编辑的流程图（DAG），而不是一次性脚本。它通过三个组件实现：技能库指导AI按步骤操作、协议层让AI实时感知当前流程状态、可视化界面让你边聊边改。在12个数据工程任务上，成功率93.3%，比普通AI助手便宜72.5%，快49.9%。它不是你明天就能用的产品，但指向一个趋势：AI生成的东西将不再是黑箱，而是你可以随时动手调整的活文档。
📄 原文摘要(英文)
Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the NL2Pipeline gap. To bridge it, we introduce DataFlow-Harness, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines DataFlow-Skills for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and DataFlow-WebUI, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, DataFlow-Harness achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency.