Publish a Databricks table to Reltio using AgentFlow™ Quality

Learn how to connect to a Databricks source, select a table, and publish it to Reltio using AgentFlow™ Quality.

Attention: This feature is available to limited users through the Reltio Early Access (EA) program. Interested in finding out more about this feature or participating in our EA program? Get details in topic Early Access (EA) features.

AgentFlow™ Quality maps source table columns to Reltio entity attributes and creates a Data Loader job. For example, you can publish a Databricks customers table as HCP profiles. No file export or re-authentication is required, the entire workflow uses the same connection and table within a single conversation.

Note: If you have already completed a data quality assessment for a table and want to publish it, see To review the mapping and publish the data. AgentFlow Quality reuses the same connection and table from the conversation.

Prerequisites

Before you begin, ensure that you have the required system roles and Databricks connection details:

The following system roles to access AgentFlow Quality:
- ROLE_AGENT_FLOW_QUALITY
- ROLE_EXECUTE_AGENTS
- ROLE_EXECUTE_MCP.
- ROLE_DATALOADER
Access to a Databricks account
Connection details for your Databricks workspace:
- Server hostname
- HTTP path
- Access token
- Catalog name
- Schema name

To connect to a Databricks source

Open AgentFlow Quality.
Select the required tenant.
Select Start Data Load.
The Data Loader orchestrator appears.
Select Databricks to connect to your source data.

In the Connect to Databricks page, enter the following connection details.

Connection details	Description
Connection name	A label to identify and save the connection for later reuse.
Server hostname	The hostname of your Databricks workspace.
HTTP path	The HTTP path of the Databricks SQL warehouse you want to connect to.
Access token	A Databricks personal access token to authenticate the connection.
Catalog name	The Unity Catalog catalog that contains the tables you want to load.
Schema name	The schema within that catalog that contains the tables you want to load.

Select Connect.
AgentFlow Quality validates your credentials, saves the connection under the name you provided, and displays the Select tables screen for the catalog and schema you provided.
Select the checkbox for the table you want to load, then choose Select.
The suggested mappings appear.

To review the mapping and publish the data

Review the suggested mapping between the source table columns and the target Reltio attributes.

AgentFlow Quality groups the mappings by the following confidence levels.


Confidence level	Description
High	The source column name and data type closely match a Reltio attribute.
Medium	The source column partially matches a Reltio attribute. Review the mapping carefully before accepting.
Skipped	The source column has no matching attribute, so AgentFlow Quality does not include it in the mapping.

Select the checkbox for each mapping you want to include, or clear it to exclude the mapping.
Select Accept.
The Confirm load summary appears.
Review the Confirm load summary.
The summary lists the table, object type, and number of accepted mappings.
Select Confirm.
On completion, AgentFlow Quality displays a summary of the data load job in the conversation.

Result

AgentFlow Quality runs the data load and returns a completed load summary that includes the following details:

The success rate
The number of records loaded, failed, and total
A load outcome chart
Job details, such as the source table, object type, load type, and job ID

Tip: If any records fail in the data load job, ask AgentFlow Quality to help diagnose and resolve the issue directly in the conversation

Verification steps

To verify the data load, check the results in the conversation, Console, and Hub:

In the conversation, review the summary of the data load job.
In Console, confirm the job status and any load errors by performing the following steps:
1. In a new browser tab, sign in to your Reltio MDM tenant.
2. From the Applications menu, select Console.
3. Select Data Loader.
4. On the left navigation panel, select Job Status.
5. Select the COMPLETED tab.
6. Identify the job using the job ID provided in the conversation.
In Hub, confirm the loaded records match the source table by performing the following steps:
1. In a new browser tab, sign in to your Reltio MDM tenant.
2. From the Applications menu, select Hub.
3. On the left navigation panel, select Search.
4. Search for the loaded records and confirm the attribute values match the source table.

Unify and manage your data

Publish a Databricks table to Reltio using AgentFlow™ Quality

Footer