In AI Workbench, data scientists can give marketing teams the ability to supply data and information to an AI model via a simple notebook UI, without having to edit or write any code. For example, if an AI model calculates a customer score based on different BlueConic profile properties, dialogues, segments, etc., marketing teams can supply the values for the application in an easy-to-use UI in the Parameters tab of AI Workbench.
To edit parameters for an AI Workbench application:
- In AI Workbench, open the Jupyter notebook that contains your application.
- Select the Parameters tab and choose values to supply data to the application.
For example, in the My Segment field, the application calls for a BlueConic segment. We chose All Visitors for this value.
- Continue selecting values as called for in your application.
In our example, the next field calls for a profile property, and we chose First Visited Date.
- Save your settings.
The next time this note book runs, it will use the values you supplied.
What are parameters in AI Workbench?
In AI Workbench applications, developers who write Python code might call for marketers to supply certain variables to supply data to the AI model -- for example, which segments of users profiles should the model use? What values need to be entered or chosen? Marketers provide these values in the Parameters tab, and AI Workbench uses that BlueConic data in the AI model.
What types of BlueConic values can be a notebook parameter?
Valid parameter types include these types of BlueConic data: channel, connection, date, datetime, dialogue, external_tracker, int (for integer), listener, objective, notebook, profile_property, profile_property_unique, segment, str (for string), and text. Developers specify which parameters are used in the code and give them a parameter name. For example, the model might call a listener, and marketing teams supply the values they want to use, for example, "Shopping Cart Listener."