This article covers some of the main errors that can occur in Search and how to fix them.
No data for the time range selected
This can happen when you ask a question like Spend this year but your data is not up to date. When you use the phrase this year, Anna interprets it as the calendar year we are in when you ask the question.
In this example, the question was asked in 2020, therefore Anna is looking for Spend between January and December 2020. As my data is only updated to 31 October 2019, Anna doesn't have enough information to answer my question.
Rephrasing a question
Sometimes Anna may ask you to confirm her understanding of a question. Anna does this when she thinks you've asked her about something that's not in your data, like if you make a typo.
In this example, Anna will try and suggest a segment or measure that she thinks is close to what you were trying to type. You can use the segment she's selected, tell Anna to ignore your typo, or try a new phrase.
If you select the segment or measure that Anna has suggested (in this example, Anna thinks dep is close to Ordering Department), you can teach her to remember that association going forward. So now, any time I type "dep", Anna will know I mean Ordering Department - handy!
If you select No. Let me try a new phrase, you will be prompted to enter your new phrase.
No clear drivers for this change
If you've drilled down to the lowest level possible in your dataset, Anna may not be able to identify What caused this? in your data as there are no clear factors for the change.
If you have any questions, please contact us at email@example.com.