AI写代码不再是一次性脚本，而是可拖拽的流程图
现在的AI编程助手（如Claude Code）虽然能写代码，但生成的脚本是“一次性”的——你没法像拖拽流程图那样随时修改它。这篇论文搞了个平台，让AI直接生成可编辑的流程图（DAG），而不是自由文本脚本。具体做法是：把数据处理拆成一个个“技能块”，AI通过增量修改来搭建流程，同时平台实时展示当前状态，你还能在可视化编辑器里手动调整。在12个数据工程任务上，它的成功率93.3%，比普通Claude Code便宜72.5%、快49.9%，而且成功率只比最好的基线低0.9个百分点。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脚本，而是你能像搭积木一样随时改的“活”工件。
📄 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.