AI Tagging Agent (Private Beta)

Overview

The AI Tagging Agent helps you keep metadata consistent and organized by automatically tagging tables, dashboards, and columns. Using natural language, administrators can define tagging rules that run daily to ensure metadata stays accurate and up to date.

Key Features

• Create tagging rules using natural language

• Validate results in the preview table

• Apply tags in bulk to tables, dashboards, and columns

• Automatically execute rules daily

Getting Started

Prerequisites

• Admin access

  • Admins can create new agents, view all agents, and enable or disable them.

• AI features enabled in the Admin Panel

Basic Workflow

1. Enable AI features in the Admin Panel.

2. Go to the AI Agents section in the Ask AI page.

3. Create a new agent by writing tagging instructions in natural language.

4. Review the preview to confirm the agent’s interpretation.

5. Type "save", "confirm", or a similar instruction to save the agent and schedule daily execution.

6. Once created, the agent is enabled by default and added to a queue for execution. The first execution may take some time if other agents are ahead in the queue. After the initial run, the agent will execute daily.

7. On the AI Agents page, you can enable, disable, or delete agents.

Tagging Conditions

You can define rules based on different criteria, such as names, dates, lineage, popularity, or existing tags:

• By name: Add a PII tag to all columns named "customer_email"

• By date: Tag tables created in the last 30 days with "new_data"

• By lineage: Tag tables with no downstream dependencies as "endpoint"

• By popularity: Tag dashboards with popularity > 80 as "gold"

• By data source type: Tag all snowflake tables as "Tested"

Limitations

• Supports only tables, columns, and dashboards.

• Agents can be created using only the following attributes: name, data source type, popularity, created on, and updated on.

• Updated on and created on are available only for tables and columns. Dashboards do not support these filters.

• Lineage can be used only to check whether it exists or not — filtering by specific lineage items is not supported.

Step-by-Step Tutorial

1. Navigate to AI Agents

• Open the Ask AI page.

• Click on the AI Agents item.

2. Create a New Agent

• Click Create Agent.

• Enter a natural language instruction describing your tagging rule.

List all tables with the name “Log”

3. If needed, update the filter.

Update the filter to also include tables the name includes “analytics”.

Note: using “update” is important, otherwise the prompt will create a new filter with only the new instruction.

4. Add the tag

Add "analytics" tag

5. Save the agent

Type "save", "confirm", or a similar instruction to save the agent.

Confirm

Once the agent is running, you can track its progress in the list view and visit the chat to update the prompt.