Establish data quality standards for data sets in your catalog, create rules for the data elements in the data sets, and ensure that the data meets the established data quality standards with the help of the data quality rule recommendation skill of the data quality agent.
You can ask CLAIRE GPT to assess a data set and recommend suitable data quality rules. To recommend rules, the data quality agent considers the business context from your prompt to identify the critical data elements within the data set. After the agent identifies the critical data elements, it recommend data quality rules that are contextual to the identified data elements.
Optionally, you can ask CLAIRE GPT to recommend additional rules beyond those that are contextual to the identified data elements. To recommend additional rules, the data quality agent considers the data profile or a sample row of the data set.
The data sets for which you want CLAIRE GPT to recommend the rules might not have associated rule templates. If there are no data quality rule templates associated with the data sets in Data Governance and Catalog, CLAIRE GPT recommends rules directly from the rule specifications in Data Quality. If no rule specifications are available in Data Quality, CLAIRE GPT can generate new rules. For more information about how CLAIRE GPT generates data quality rules, see Data quality rule generation.
You can get rules for data sets that don't have manually created or associated rules. You can then use the recommended rules to establish data quality criteria for the data set. By defining the criteria, you set standards for the data based on various dimensions such as accuracy, completeness, and consistency. You can accept or reject rule recommendations. If you accept a rule recommendation, a rule occurrence is then created for the data elements in Data Governance and Catalog, where you can review your data for discrepancies.