Add AI-driven rule suggestions

The section shows you how to generate AI-based rule suggestions for specific columns directly within the job workflow. This feature analyzes your column metadata and profiling statistics to suggest relevant rules with plain-language explanations, reducing the time and technical expertise needed to create comprehensive data quality monitoring.

Note The AI never accesses your actual data rows, ensuring privacy and security compliance.

Prerequisites

• You have an existing Data Quality Job with at least one run.

• The Data Quality Pushdown Processing Edge capability is enabled for your data source.

• You have the Data Quality Editor or Data Quality Manager resource role.

• The AI Rules suggestion setting is turned on. This setting is found under Settings > Data Quality > Rules.

• The associated feature flag is enabled for your pushdown connection:

  • Snowflake - dataquality.aiRuleSuggestions.enabled

  • Databricks - dataquality.aiRuleSuggestions.databricks

  • Big Query - dataquality.aiRuleSuggestions.bigquery

  • SQL Server - dataquality.aiRuleSuggestions.sqlserver

  • Redshift - dataquality.aiRuleSuggestions.redshift

  • Oracle - dataquality.aiRuleSuggestions.oracle

Steps

1. On the main toolbar, click → Data Quality.
   The Monitoring Overview page opens to the available data sources in your environment, showing their monitoring coverage and other high-level metadata.
2. Perform one of the following to open the Rule suggestions page:
   • On the Monitoring Overview page, select a pushdown job and select Add rule > Suggest rules with AI.
   • In the sidebar navigation on the left, click Rule suggestions and select a pushdown job from the Job drop-down.
3. All columns are selected by default. To exclude specific columns from the analysis, select them in the right pane and click .
4. Click Analyze columns.
   All suggested rules show by default. The suggested rules are categorized by data quality dimension.
5. Click a suggested rule to view the details in the Preview pane. You can also use the Previous and Next rule buttons to review each suggested rule. The details in the Preview pane include:
• Primary column
• Data type
• Description
• SQL query
• AI rationale
6. If necessary, deselect a rule by clearing the checkbox in the table or by clicking Deselect rule in the Preview pane.
7. Click Apply rules to automatically create the selected rules.
   The selected rules are immediately added to the Monitors tab within your job. A confirmation message shows that the rules have been applied, and the job is ready to run with the new monitoring in place.

What's next

• About rule-level settings
• Go to the Job Details page to:
  • Manually re-run your job and view the output of the rule monitor in the Monitors tab.
  • View the output of the rule monitor in the Monitors tab after your scheduled job runs automatically.