Manage AI-Assisted features - Precisely Data Integrity Suite

Data Integrity Suite
Product
Spatial_Analytics
Data_Integration
Data_Enrichment
Data_Governance
Precisely_Data_Integrity_Suite
geo_addressing_1
Data_Observability
Data_Quality
dis_core_foundation
Services
Spatial Analytics
Data Integration
Data Enrichment
Data Governance
Geo Addressing
Data Observability
Data Quality
Core Foundation
ft:title
Data Integrity Suite
ft:locale
en-US
PublicationType
pt_product_guide
copyrightfirst
2000
copyrightlast
2026

The AI functionality within Data Integrity Suite allows you to configure AI capabilities while maintaining strict adherence to security and acceptable AI policies. AI Manager supports integrating trusted and vetted Large Language Models (LLMs) so teams can control the models used in their workspace.

Note: You must have the Workspace Manager role to access the AI page. Also ensure that the required LLM connections are available in your workspace. For first-time setup, create a new LLM connection.

To access AI Manager:

  1. Go to Configuration > AI.
  2. The AI Manager is divided into two pages:
    • Features to enable and manage AI capabilities.
    • LLM Connections to create and manage reusable model connections.

These provide a structured approach to manage AI capabilities and LLM configurations at the workspace level.

Manage AI features

You must create at least one LLM connection before you configure AI features. If no LLM connection exists, the Features page displays a notification. Select Create LLM Connection from the banner, or open the LLM Connections page to set up a supported provider. After you configure a connection, return to the Features page to turn on AI capabilities.

The Features page controls the AI-powered capabilities available to your workspace. From this page, you can turn AI on or off, set your default LLM preference, browse AI features by product area, and review feature health.

  1. Go to Configuration > AI.
  2. Open the Features page.
  3. Use the AI Features within Data Integrity Suite toggle to turn AI capabilities on or off for your workspace.
    When the toggle is on, supported AI features are available throughout Data Integrity Suite.
  4. In the Large language model (LLM) preference priority area, arrange the LLM connections in the order you want AI Manager to use them.
    The first available model in the priority list becomes the default model for AI features, unless you override the model for a specific feature.
  5. To add another LLM connection to the priority list, select +.
  6. Expand a product area to view the available AI features.
    Product areas can include Catalog, DQ Pipelines, DQ Rules, DQPlus, and Foundation.
The feature list shows each AI capability, its current health, the model or model family it uses, and whether the feature uses the workspace default or a feature-specific override.

The feature table includes the following columns.

Column What it shows
Feature Name of the AI capability.
Status Current execution or configuration status of the feature.
Model or Model Family The model the feature uses, or Inherited if it uses your workspace default.
Enabled Whether the feature is turned on.
Override Opens the override panel, where you can assign a different model to this feature.

Each AI feature displays a status that tells you its current health.

Status Meaning
Success The feature is configured correctly and ready to use.
Warning The feature is working but needs your attention.
Error A configuration issue prevents the feature from using its assigned model.
Failed The feature failed to initialize or run.

If a feature shows a Warning, Error, or Failed status, select the status indicator to view details. The details panel shows the capability name, agent type, model in use, configuration source, a description of the issue, and suggested actions to resolve it.

Each feature uses its model in one of the following ways.

  • Inherited: The feature uses the default model from your workspace LLM preference priority. When you change your workspace default, all inherited features use the new model.
  • Overridden: The feature uses its own assigned model instead of your workspace default. Only that feature is affected by the override.

Use these practices when you manage AI features.

  • Configure your workspace LLM preference before setting up individual feature overrides.
  • Use feature overrides only when a specific AI capability requires a different model.
  • Check feature statuses regularly to catch configuration issues early.
  • Address warnings and errors promptly to keep AI functionality running.
  • Remove feature overrides when a custom model is no longer needed.

Override an AI feature model

By default, each AI feature uses your workspace-level LLM preference. Features that use the default show Inherited in the Model or Model Family column. If a feature needs a different model, you can override its configuration.

  1. Expand the category that contains the feature.
  2. Select Override.
  3. In the Override panel, turn on the feature if necessary.
  4. Select your preferred LLM connection.
  5. Review the Feature Execution information, including status, capability, agent type, model in use, and source.
  6. Select Override.
The selected model is used only for that feature.

Reset an AI feature model to the workspace default

Reset a feature-specific override when the feature no longer needs its own model assignment.

  1. Open the Override panel for the feature.
  2. Select Reset to Default.
The feature uses your workspace-level LLM preference, and the Model or Model Family column displays Inherited.

Configure LLM connections

The LLM connections page can be used to configure LLM connections at the workspace level.
Note: Once a new LLM connection has been established, it can be reused across all the features.

To configure this:

  1. Go to Configuration > AI.
  2. Open the LLM Connections page.
  3. Select Add LLM Connection.
    1. Provide a name and a suitable description to the connection.
    2. Select the LLM provider. Currently, Data Integrity Suite supports the AWS Bedrock LLM provider.
    3. Select the associated AWS region.
    4. Enter the authorization details. Enter the AWS access key ID and AWS secret access key.
    5. After you enter all details, select Test to validate the connection details. After successful validation, a confirmation message appears.
    6. Select Add. The configured LLM connection appears in the list.
  4. Open the context menu for the associated connection, then select Edit, Test, or Delete.
Tip: Your AWS account must have read and write access to Bedrock, as well as access to the required LLM families (such as Claude Sonnet and Mistral). All other permissions are optional and are typically included only for convenience.