Auto-generate rule expression for pass conditions - 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 auto rule expression generation feature lets you create advanced pass conditions in Quality rules and pipelines by describing logic in plain English. This AI-powered capability interprets user intent and generates expressions, reducing manual effort.

This feature is available in the Basic and Advanced tab of the Pass conditions, Add Evaluated Rows Filter section in Create Rule page, and Condition tab in Step Configuration of a quality pipeline. Use the AI Assist button to generate expressions.

Note: To use the auto-generate rule expression feature on the rules page, ensure that the Generate Rule Expression functionality is enabled at the workspace level under the AI tab. If it isn't enabled, the AI Assist button will not be visible within the rule creation interface. For further guidance, refer to the AI manager documentation.

Benefits

  • Simplified expression creation: You can describe your logic in natural language, and the application converts it to a valid expression by using field names and data types.
  • Reduces manual effort: You don't need to write complex scripts as the AI handles the conversion, saving time and minimizing mistakes.
  • Consistent and accurate output: Expressions are generated using standardized grammar and metadata, ensuring uniformity across rules and pipelines.
    Tip: To ensure your expression is generated accurately, follow the instructions below:
    • Use valid field names from your dataset. The application uses these names and their associated data types to construct accurate expressions.
    • Avoid unsupported keywords, such as Value alias, which can prevent the application from generating a valid expression.
    • Verify prompt accuracy. If your prompt references the fields that do not exist, expression generation may fail.
    • Refine unclear prompts. When needed, revise your input using valid field names and supported syntax.
Tip: Expressions are generated in-session and only saved when you click Create or Update.

To generate expressions in pass conditions:

  1. Go to Quality > Rules.
  2. On the Rules page, click Create Rule.
  3. Select the target assets to evaluate, and then define pass conditions.
  4. Click the AI Assist button present beside the pass conditions section to open the expression generation panel.
  5. In the description box, enter your logic in plain English. Include details for the relevant datasets or fields.
  6. Click Generate. The application will automatically generate an expression for the pass condition based on the inputs.
    Tip: If the generated pass condition doesn't produce the desired outcome, you may revise the prompt and select Generate to create a new pass condition based on the specified parameters. Once the expression meets your requirements, you can either copy the generated expression or select Apply to implement the pass condition within the rule.
  7. Click Create to save the rule with the generated expression and other details.
Note: The application will generate an appropriate exception if invalid prompts are entered, such as those that are overly generic or not recognizable within the context of the established rule. In addition, exceptions will be triggered in cases of errors relating to the LLM connection or server issues.

AI generated test data to validate rule expressions

The AI-powered data generation feature creates sample test data to help you check rule expressions for both pass conditions and row filters before applying them to your datasets. It produces a set of records to verify expression correctness and intended outcomes.

To validate test data generated by expressions in the row filters or pass conditions in the rules page:

  1. Define the conditions in the rows filter or pass conditions on the Create Rule page.
  2. Click Test with AI Generated Data.
  3. The conditions in the filters are evaluated, and the sample data is generated.
  4. The Test with AI Generated Data page displays the following details:
    • Expression using which the data is generated.
    • Generated data: The generated data is presented in a tabular format. The Result column is fixed and indicates whether each value has satisfied the specified conditions and passed or did not meet the defined conditions and failed. All other columns on the table will be displayed as per the expression.
      Tip: The sample displays a maximum of 20 records (10 Pass and 10 Fail), offering an accurate representation of how the conditions are evaluated.
  5. The data in each of the columns in the table can be sorted as needed.

Once you are satisfied with the generated sample, you can proceed with the next steps of creating the rule. If you notice any discrepancies in the generated sample, you can modify the conditions in the filter and regenerate the sample data.

Note: Sample data will be generated exclusively for valid expressions. If an invalid expression is entered in the conditions, the Test with AI Generated Data feature will be disabled.