Large Language Models (LLMs) have revolutionized natural language interaction with data. The "holy grail" of data analytics is to build autonomous Data Agents that can self-drive complex data analysis workflows. However, current implementations are still limited to linear "ChatBI" systems. These systems struggle with joint analysis across heterogeneous data sources (e.g., databases, documents, and data files) and often encounter "context explosion" in complex and iterative data analysis workflows. To address these challenges, we present DeepEye, a production-ready data agent system that adopts a workflow-centric architecture to ensure scalability and trustworthiness. DeepEye introduces a Unified Multimodal Orchestration protocol, enabling seamless integration of structured and unstructured data sources. To mitigate hallucinations, it employs Hierarchical Reasoning with context isolation, decomposing complex intents into autonomous AgentNodes and deterministic ToolNodes. Furthermore, DeepEye incorporates a database-inspired Workflow Engine (comprising a Compiler, Validator, Optimizer, and Executor) that guarantees structural correctness and accelerates execution via runtime topological optimization. In this demonstration, we showcase DeepEye's ability to orchestrate complex workflows to generate diverse multimodal outputs -- including Data Videos, Dashboards, and Analytical Reports -- highlighting its advantages in transparent execution, automated optimization, and human-in-the-loop reliability.

翻译：大型语言模型（LLMs）已彻底改变了与数据进行的自然语言交互。数据分析领域的“圣杯”在于构建能自主驱动复杂分析流程的自治数据代理。然而，当前实现仍局限于线性的“ChatBI”系统。这类系统在处理异构数据源（如数据库、文档及数据文件）间的联合分析时存在困难，并且在复杂迭代的数据分析流程中常遭遇“上下文爆炸”问题。针对这些挑战，我们提出了DeepEye——一个生产级数据代理系统，采用以工作流为中心的架构来确保可扩展性与可信度。DeepEye引入了统一多模态编排协议，实现了结构化与非结构化数据源的无缝整合。为缓解幻觉问题，它采用基于上下文隔离的分层推理，将复杂意图分解为自主代理节点（AgentNode）与确定性工具节点（ToolNode）。此外，DeepEye融合了受数据库启发的工作流引擎（包含编译器、验证器、优化器与执行器），通过运行时拓扑优化保障结构正确性并加速执行。在此演示中，我们展示了DeepEye编排复杂工作流以生成多样化多模态输出（包括数据视频、仪表板及分析报告）的能力，突显了其在透明执行、自动优化及人在回路可靠性方面的优势。