Knowledge Management Permissions: Query Metadata

This article explains how to control the data and knowledge scope that AI assistants can reference through query metadata.

Feature Overview

When deploying AI dialogue systems, it is typically necessary to implement fine-grained control over the available scope of "Knowledge Bases / AI Assistants / Conversation Platforms" due to different user permissions and usage requirements.

In MaiAgent, you can use query metadata attached to different conversation/identity levels to determine "what content this person/conversation can reference."

What is Query Metadata?

Query metadata is a set of dynamic conditions that limit the query scope, allowing you to specify the data content that users can query under a specific conversation platform, such as "knowledge bases, FAQs, documents matching tag conditions," etc.

It does not replace roles or contacts, but rather allows these identities to "function conditionally," implementing conversation-level least privilege control.

Roles / Contacts / Conversations are containers; query metadata is the conditional restriction that actually controls the visible scope

Learn more through the following articles:

• Contacts

• Role Permission Management

Permission Hierarchy Concept

Before service construction, the Agent determines all knowledge bases that can be referenced at this time through query metadata at different levels. The permission hierarchy reference order is as follows:

AI Assistant > Conversation Platform > User (Conversation / Contact / Role) > Query Metadata > Query Permissions

You can specify permissions at each level using a graphical interface or JSON format

Refer to the following documents for operations:

1. Getting Started—Using the "Query Builder"

2. Technical Personnel Manual: JSON Interface Configuration Guide (Contact, Web Chat Embed Settings)

• Contacts / Roles are identity containers

• Conversations correspond to internal dialogue scenarios where filtering can be used to control the knowledge bases utilized

• Query metadata is the "collection of filter conditions" actually executed during conversation

Document Filter Condition Judgment Hierarchy

Through layer-by-layer transmission, query metadata becomes the actual decision-making basis for AI response logic

Practical Application Scenarios

---

Summary: The Value of Query Metadata for Enterprises

🎯 Multi-dimensional Identity Cross-Control (Role + Region + Product Line)

🎯 Real-time Query Control: No need to duplicate assistants; simply change conditions to adapt to scenario switches

🎯 Flexible Large-scale Knowledge Base Management: Tags and knowledge bases can be split and authorized according to scenarios

It is recommended to incorporate query metadata as a core part of your product architecture, enabling enterprises to achieve maximum authorization flexibility with minimal configuration, ensuring knowledge security while improving conversation experience and operational efficiency.