Last week, we announced early access for Database Connectivity. We're rapidly enhancing this powerful capability, and the latest update is an exciting one.
Create queries, assertions, and variables with AI
If you're new to writing database queries or want a jumpstart constructing a complex query, you can take advantage of our new AI-assisted query generator. Not only will this help you author an effective query using a natural language description of your objective, but you can also describe variables you want to store and assertions you want to make from the query's results.
Look for the AI text input prompt in the database query step of the mabl Trainer.
Generating a query, assertion, and variables using generative AI
Try it out
Before you start, make sure to update to the latest version of the mabl Desktop App: Help > Check for updates. During the early access period, workspace owners can enable Database Connectivity on the Labs page: Settings > Labs.
- Go to Configuration > Database connections
- Create a new database connection with all the connection details required to connect to your database.
- When creating a web or mobile test, create a new database query step directly in the mabl Trainer.
- Type what you'd like your query to do in the AI prompt as shown above. Feel free to include details about what assertions you want to make against the returned data set, as well as what you'd like to store as variables in the test.
- Click Generate.
- Review the query for accuracy. If your prompt included creating assertions or variables, check the accuracy of any auto-generated assertions and variables.
- Save the step as a one-time or reusable query.
Important considerations
- As with any generative AI capability, the results are not fully predictable, and errors can occur. Be sure to double-check any results before incorporating into your tests.
- Ensure the credentials that are used to set up the database connection include permissions to access the metadata table. The specific objects that must be accessible are information_schema.columns for MySQL and
syscolumnsandsysobjectsfor Microsoft SQL Server. - While the feature is in the early access stage, users may notice imperfect functionality.
We recognize that some organizations have limitations and policies around the use of generative AI. These features are built on top of Google Cloud's AI tools, whose terms of service do not allow use of that data to train Google's general AI models. Furthermore, our generative AI features do not train on, or use, customer data across workspaces.
If you have any concerns about these changes or the use of generative AI in mabl, please reach out to your customer success manager about next steps.