Extract business rules from an uploaded file or prompt that contains data quality rule descriptions in natural language, sample data, or a specified catalog source, and converts them into data quality rule specifications in Data Quality with the help of the data quality rule generation skill of the data quality agent.
If you upload a CSV or Microsoft Excel file that contains data quality rule descriptions in natural language, or the file contains sample data, or if you specify a catalog source from which to retrieve a data set, CLAIRE GPT uses the data quality rule generation skill of the data quality agent to automatically extract business rules and convert them into data quality rule specifications.
When you ask CLAIRE GPT to generate rule specifications for a data set, CLAIRE GPT analyzes the critical data elements of the data set to generate rule specifications.
To ensure that consistent and standardized reference data is used for generating the data quality rules, you can ask CLAIRE GPT to use a dictionary. When CLAIRE GPT generates a data quality rule specification and can't find the specified dictionary in Data Quality, it automatically creates the dictionary for the rule specification.
After you allow the agent to publish the rules, you can see the rule specifications in the project folder you specify. By default, the rule specifications are saved in the CLAIRE folder within the CLAIRE project in Data Quality. In the agent log, you can get a summary of the generated rules, distribution of rules across different data quality dimensions, and a list of the rules that were not generated. If you chose to not test the rules that were generated, the log indicates the same.