Cassie

This article kept me from pulling my own hair out. Thank you!

Hey Alice,

I'm not sure if this is a help, but under all articles, you can filter by labels. It won't pull up a list of all labels, but if you say, type an a, it'll show a list of all labels starting with a. If you type the letter b, it'll show you a list of all labels starting with b, and so on. 

If you see a label in your "a" list that you'd rather do away with, maybe you could select that label, see which articles use that label, and go in and delete the label that way? It's been a couple of years since I used that function in Zendesk, but I saw your question and thought I'd have a go at it. Good luck!

I noticed that any time a customer provided a model or part number, the bot wasn't replying in a helpful way. To combat this, I created an answer with maybe twenty examples of alphanumeric model/part numbers. This worked wonderfully to redirect the conversation until someone responded, “prop 65.” 

While the goal is to answer all questions well, we must respond to any compliance questions specifically and carefully. Like others, I needed to create a separate answer specific to Prop 65, which in fairness, I would have done anyway, but the ability to direct the bot with “this, not that,” or exclusionary training would be a powerful tool in my toolbelt. 

We aren't quite at a place where we are ready to turn generative AI on, so Bot must suggest articles or follow its training. I've noticed that it tends to shy away from article suggestions, even though this behavior is turned on. In the above example, there are several articles in our help desk, one even labeled Prop 65, and all with labels to help drive the customer in that direction. I am a little surprised that it would bypass the exact wording of an article title and reply with similar wording in a training phrase at all. 

To Kyna's point, we also have several similar sounding paths. What I've done to combat this is start with verification. For example, there are several issues that could come up with a fireplace. I start with the question, “does this request involve a fireplace insert?”, yes or no. This step is called present options. I then build in more steps using present options if they respond yes. They can specify whether the fireplace is damaged, an operator's manual is needed, if their request is about operation/usage, etc. You could try the same thing with verification: present options for ID verification or Address verification. I hope that helps :) 

I have some articles with videos that refer to an item by its name and I want to add labels with the model number. I see above that prefixes/suffixes don't matter (ex. update vs. updated), but how far can I push that? All colors of the item would start with the same four numbers, but I don't seem to effectively be able to use just those four numbers as a label.