Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Chint Group explores AI agents with SelectDB

AI summary

A report compiled from a Doris Summit 2026 presentation describes Chint Group’s use of large language models and agents with its SelectDB platform. The company is exploring intelligent anomaly diagnosis, hybrid retrieval for data assets, and natural-language queries and scheduled analysis reports. Its architecture uses application services and database permissions to limit access to authorized data, while a temporary DuckDB query layer separates agents from production SelectDB credentials. One example generates a Token usage report and pushes it to users through Feishu. Planned work on multimodal knowledge governance remains exploratory and unverified.

In-depth insight

The described architecture shows how agents can be connected to concrete data workflows while limiting their access to authorized data through application services, permissions, and an intermediate query layer.

在 Doris Summit 2026 上,许继良(正泰集团 大数据负责人)分享了正泰集团基于 SelectDB 的 AI 数据应用实践。本文整理自该演讲。

随着企业数字化建设不断深入,数据平台积累的数据资产日益丰富。如何让数据更容易被发现、理解和使用,成为企业数据平台建设的新课题。

对于大型集团企业而言,数据平台不仅需要提供稳定的数据存储与查询能力,还需要支撑日常运维、数据资产管理和业务分析等工作。传统依赖人工排查、关键词检索和固定报表的方式,已逐渐难以满足日益增长的智能化需求。

正泰集团基于现有 SelectDB 数据平台,结合大模型与智能体技术,围绕智能异常诊断、数据资产智能检索和智能分析报告三个场景展开探索,推动 AI 能力融入数据平台的日常管理与业务应用。

一、业务挑战与整体建设思路

1.1 痛点与挑战:数据平台如何更好地支撑智能化应用

随着集团数字化建设不断深入,正泰集团的数据平台逐步沉淀了大量数据模型、业务指标和分析报表,并建立了相应的数据开发、资产管理和数据服务体系。在平台持续建设和运营过程中,团队面临三个方面的挑战。

#Chint Group#SelectDB#SelectDB Manager#DuckDB#Feishu

Original · 13 min readRead the original
Group chat

No comments yet. Start the conversation.