Configuring AutoQL

Stage 1: Connect

We'll work with you to configure an encrypted, read-only connection between our cloud and your database(s). Without storing your data, this connection allows us to train our model, execute queries, and pass data back to you. We use thorough security practices to make sure none of your users’ data ends up where it shouldn’t. You’ll be able to configure access and permissions for individual customers and users later on.

Stage 2: Train

We begin with unsupervised machine training based on our system’s current understanding of typical database structures, allowing us to tailor our model to your app and deliver a feature that your users can operate intuitively. Semi-automated training is also available if you wish to customize certain queries to fit terms or jargon that are unique to your business.

Stage 3: Implement

Use any of our supported JS components to integrate our flexible front end components seamlessly, letting your users query their data from anywhere in your application. All components are open source. Fork and customize them to suit your needs. If you’re into DIY, you can build on top of our current API. We’d love to see the experiences you build to answer your users’ questions as they come to mind!

Stage 4: Query

Your users’ conversational English will be sent up to our cloud and translated into a query language appropriate for your database. Depending on how you’ve built your integration, this query language can be: returned to you, run on your database, then returned for you to display to your user, or, if you’re using our components, completely executed and visualized for your users.