SQL Query Assistance Technical Overview

Overview

Monte Carlo's SQL Query Assistance feature uses Amazon Bedrock to generate recommendations for custom data quality monitors.

We've created this section to provide a technical overview of the SQL Query Assistance feature and answer frequently asked questions. For technical specs, such as Model Types and Versions click here.

Note: Data Sampling functionality must be enabled in order to use the SQL Query Assistance feature.

How the SQL Query Assistance Feature Works

The SQL Query Assistance feature uses AI and LLMs alongside native integrations to analyze metadata and aggregated statistics, in order to generate monitoring recommendations in the form of SQL statements.

All monitoring recommendations are fully controlled and reviewable by the customer; customers can accept or reject suggestions.

Data Privacy

All data processed by the SQL Query Assistance feature is stored transiently in-memory. Upon termination of the job, all data is discarded.

The SQL Query Assistance feature relies on AI Models provided by Amazon Bedrock. Amazon Bedrock is listed on our Subprocessors page. The specific model we use in production isus.anthropic.claude-3-5-haiku-20241022-v1:0(for the US region, with equivalent models in other regions).

See Privacy Considerations for the SQL Query Assistance feature for additional information.