In this document, we’ll cover the top tips and tricks for setting up Zoë, Zenlytic’s AI analyst.
When thinking about how you’re defining your data model for use with Zoë, ask this question.
Could a talented data analyst answer questions using this data model on their first day on the job before they have any other context on the business?
If the answer to that question is yes, then Zoë will perform great! If not, use some of the tips below to encode more business context, so Zoë knows what metrics to choose in which situations.
Clearly naming your metrics (measures) and dimensions is key for Zoë to perform well for you. If you have two revenue metrics defined as Revenue first and Revenue second, Zoë, like a human analyst, will have no idea which one to pick.
However, if you define those two values as Gross revenue and Net revenue Zoë will have no problem distinguishing between them and when to use one vs. the other. If an outside analyst could read all your metric definitions and understand which ones to use in the right cases, Zoë would also be able to.
Zoë will never index your data unless you explicitly tell her to. This protects your privacy and makes sure we never index sensitive or regulated data.
Many times you’ll want to be able to ask questions like “How many orders do we have in fulfillment placed more than a week ago?” But if the fulfillment category is hidden in a field nebulously called status, Zoë won’t know how to find the right filter.
Add the searchable property to the status dimension like: