让企业分析从问问题开始，转为由专家技能自动生成可验证报告。
From Question-First to Analyst-First: Domain-Expert Skills and Verified Knowledge Compilation for Proactive Enterprise Analytics
- 用可插拔的领域专家技能包，自动匹配数据表并生成分析内容。
- 离线构建可信知识库，确保每个指标都可回溯验证。
- 适合需要快速上手、无经验用户的企业级数据分析场景。
对话式分析系统假设用户已有明确问题，导致非专家面对陌生数据结构时无从下手。现有主动分析工具仅能检测预设指标层的统计异常，学术型下一步问题推荐依赖查询日志，新数据集缺乏此类数据。本文描述一个生产级分析系统，通过两个耦合的架构设计，将交互模式从‘问题优先’转为‘分析师优先’。第一，引入可插拔的领域专家‘技能’抽象：基于文件夹的、无需数据库的主题包（包含清单、阶段提示片段、关键词路由引用、报告模板及可选计算），通过确定性模式匹配自动选择，嵌入代理流程、模式探索器和报告引擎中，缺失时退化为无操作。因技能是自包含且确定性解析的，目录可无限扩展，形成开放的专家市场。第二，离线知识编译循环：代理通过DuckDB探测Parquet数据，以批评者门控机制执行逐表收敛，支持自修复重试，并通过值重叠验证连接，生成持久化模式知识，驱动持续的专家报告。每份发布的指标均通过重新执行证据SQL进行再验证，同时生成呼应报告主题的建议问题。这形成闭环：报告呈现数值，数值激发问题，点击即启动经验证的深入分析，全部在使用查询框前完成。本文给出形式化模型，并提供单租户示例证据。未做用户研究或基准测试；贡献在于架构及其可辩护性。
原文摘要 · Abstract (English)
Conversational analytics systems assume the user already has a well-formed question, leaving a non-expert facing a blank query box on an unfamiliar enterprise schema. Commercial 'proactive' tools narrow this gap only by detecting statistical anomalies over analyst-curated metric layers, and academic next-question recommenders depend on query logs that a fresh dataset lacks. We describe a production analytics system that inverts the interaction model from question-first to analyst-first through two coupled architectural ideas. First, a pluggable domain-expert 'skill' abstraction: a folder-based, database-free subject-matter pack (a manifest, per-stage prompt facets, keyword-routed references, report templates, and optional compute) auto-selected per (client, dataset) by deterministic schema matching and spliced as a cross-cutting concern into every stage of an agentic pipeline, the schema explorer, and the report engines, degrading to a strict no-op when absent. Because a skill is a self-contained folder resolved deterministically, the catalogue is open-ended: an extensible marketplace of domain experts. Second, an offline knowledge-compilation loop: an agent probes the dataset's parquet via DuckDB (zero load on production), runs critic-gated per-table convergence with self-healing retries, and data-validates joins by value overlap, producing durable schema knowledge that drives standing expert reports whose every published metric is re-verified by re-executing its evidence SQL, plus suggested questions that mirror the report agenda. These close a proactive loop: reports surface numbers, the numbers seed questions, and a click launches a verified deep dive, all before the query box is used. We give a formal model and report illustrative single-tenant evidence. We make no user-study or benchmark claims; the contribution is the architecture and its defensibility.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。