You can use labels to help with targeting for your Answer Bot triggers. Adding labels to your Answer Bot triggers is optional. Labels enable you to specify a limited subset of articles that you want to search within.
Without labels, Answer Bot searches all article titles and content to identify suggested articles. By adding labels in triggers, you can restrict the search to articles containing those labels.
When you use multiple labels in triggers, the Answer Bot handles each separately using OR logic to suggest content.
This article covers three scenarios for using labels in triggers to better target article suggestions in your web forms. For information on using Answer Bot labels in the Web Widget, see Configuring Answer Bot for the Web Widget: Filtering Answer Bot suggestions by label.
Scenario 1: Targeting customer segments
The most common scenario for when to use labels in triggers is when you have different customer segments and you want to show each segment only the relevant articles. For example, suppose you are a mobile game developer and you support both Android and iOS platforms. When you get a request from a customer who's using Android, you want to show only Android articles.
To accomplish this, create an "Android" Answer Bot trigger with the condition based on your custom field "Platform = Android." Then, configure Answer Bot using labels to include only articles that contain the "android" label.
Likewise, set up an additional trigger for the iOS platform and label.
Scenario 2: Reducing the "noise" in your Help Center
Your Help Center might contain a lot of articles, most of which you never want to be used as Answer Bot recommended articles.
In this case, review your articles and add a "use_for_answer_bot" label to ~200-300 of the best articles. This will allow Answer Bot to focus and only suggest articles that make sense.
Scenario 3: Conducting a limited trial for a specific type of inquiry
While not recommended (it's a slippery slope), some customers have proven the value of Answer Bot by focussing it on a specific type of inquiry, such as "password reset" requests.
By creating an Answer Bot trigger that looks for specific words in the subject / description, and then using labels to restrict the articles suggested, you can limit the pilot and get some quantitative data to help support a broader rollout.
Hi Zendesk team!
I was thinking that using conditional Fields together with the AnswerBot via Web Channel might be a good way to filter AnswerBot article suggestions.
Is there a way for me to do this currently?
Example on the Web form, I have a Ticket Field which has a corresponding tag. Could this tag be used as a label for the article so that AnswerBot fires it as a suggestion every time the specific answer to a Ticket Field is selected by the end user?
The native behavior of the Answer bot uses what the customer types in and searches for related articles. Would you like to control the suggested articles using tags or conditional fields? if yes, you may do so using advanced custom coding. Unfortunately, we don't have a native way to do it but Answerbot API would be a good starting reference.
All the best!
There still seems to be a lot of open question about this. I even ugraded my account for additional options.
What I did:
I think the button should be called "SAVE" maybe because those mean to very different things. However I do se the label is not there under the configuration botton.
Hi Mike! When I go to create my triggers and I click "test and configure" the three article suggestions pop up with no problem. However, there is no option to select add articles there is only an option "done". When I click that and return to my trigger set up under "list of article labels to be included" it says there are no labels currently set. How do it fix this?
If I'm understanding this right, it sounds like you may not have set any labels on your articles? If so, here's how to do that: Using labels on your help center articles
Edited - Solved - Sharing the solution!
This article states:
If I go to that article, it has nothing about using labels to filter out answerBot results with web widget. Seems like the mentioned topic has been removed?
We have received instructions from Zendesk support to use following API settings filter out the articles shown by answerBOT in widget:
Works fine! Thanks for Zendesk's support team for guidance!
So, we added label 'answerbot' to articles that we wish to show in widget, and added webWidget-settings accordingly:
You might want you your own label(s) or include the setting as part of earlier settings, but if you have done this before, should not be a problem.
If you would like to use multiple labels to define the correct article set, it is possible - just a example of the syntax:
Q1) Is it possible to exclude articles from answerbot using labels without having to assign a include label to everything else?
For example, exclude the internal agent training section we have.
Q2) We have many people working on articles daily and I'm looking for a better way to maintain this other than periodically bulk mass editing articles to re-push the answerbot inclusion label on them.
Can a label be assigned automatically by Guide Sections/Categories?
Thank you for the help,
It's not, you would think this would be way easier to implement than the reverse. We upgraded a few months back and the additional help center features all of you to bulk select articles and assign labels to them, this is the only solution right now and you have to remember to do it for every article you create. So still a pan but time is cut down. I hate to say it's 1 of 2 reasons we upgraded. The Article review and assignment features are really helpful if you have a lot of people in the Help Center. may require some training and process but might help in your case.
Is there any way to instruct Answer Bot to do one of the following two things to exclude specific content?
I've read about a dozen articles today on this topic and I don't think there's any possible way I can do either of those things, and I just need to do one of them in order to solve the problem I have which is our customers are getting served our internal articles by Answer Bot.
I do not want to bulk tag 200-300 articles to be included in Answer Bot search, I would like to exclude the 10-15 internal articles we have for employee training.
1) Restrict the article you want to exclude to agents and admins only. This way, it will not be displayed to the end-users suggestions.
2) Create labels, and add them to the articles you want to show. This way, the ones that don't have one will not be shown in the suggestions of Answer Bot. I would invite you to have a look at this article, which explains in detail how it works: https://support.zendesk.com/hc/en-us/articles/4408883075098
We ended up going with your second option and I bulk edited articles using the filters for article placement and permission so I could mass target all of the ones read by specific customers in specific areas of the site (Basically excluding internal segmented articles). Then used the article settings at the bottom to change label to "answer-bot" and identified that tag for pickup in the answer bot automation settings. I'm pretty sure most of that was covered in that article you linked for number 2, and that has helped us to greatly improve the results our bot is producing on tickets.
Is there a way to always include the same articles when the answer bot fires? For example, we have an article of top 10 viewed articles and we'd like that to be included in the list each time. Is that possible?
There's not a way to do that, but you could always add a link to this article yourself to the email notification -- see Creating and managing triggers for Answer Bot
I have exactly same request what Chad had, and think that many other people may have it.
Do you have any plan to change the function in near future?
I'm not aware of any plans to change this functionality now. I would recommend creating a feedback post in our Feedback - Help Center (Guide) since that topic is being actively monitored by our Guide product managers.
Thanks for taking the time to share this with us!
Please sign in to leave a comment.