Fiona

I'm not sure if I'm misinterpreting but, the system generated trigger says to only fire under the condition the satisfaction is unoffered. However, I see it firing every time I set the ticket to solved even those they already rated the interaction. If I see the trigger in the events of the ticket, does that mean the survey was sent even though it's not supposed to fire if there is a rating?

What is the best practice for this follow up ticket? I'm guessing it now counts towards the ticket volume etc, and it has the tags from the original ticket so it will count towards my reports for those tags.

-  If I delete the follow up ticket once the side conversation update has been addressed, would further replies create a new follow up ticket so that I'm still notified?

- If not, how can I easily identify and exclude these tickets from my reporting?

Thanks

Is there a way to edit without publishing the changes right away, just like a regular article?

I'm also seeing the same as Matt Russell.

I just tested for a question that is directly answered in our articles and it took 3 attempts and very slight rewording for the bot to understand (see screenshot). When I later attempted the second variant, it understood and answered correctly...

For "expand", I have the following feedback:

- the AI uses "Hello [name]," but we usually use "Hi [name]" (hi and no comma). Is there going to be a way to standardize this somewhere so that the AI generates our preferred greeting?

- the AI adds the greeting every time, even if only part of the text in the box is selected

- the AI writes a response that is often too formal for our usual tone of voice and defaults to "we" (e.g. we apologize...) rather than "I". Will there be a way to dictate the tone of all expanded texts? 

Thanks!

Can the bot not see content block information? I just tested the bot by typing what is literally the article title (and some other variations) and it gave the "please rephrase" reply. the only thing i can think is that the entire article is a content block.

Love this! Been testing out the 'expand' feature and it's great. 

I noticed the AI uses "Hello [name]," but we usually use "Hi [name]" (hi and no comma). Is there going to be a way to standardize this somewhere so that the AI generates our preferred greeting?

Thanks!

Hi

I'm confused - if it's advanced AI, can it just read the question the customer has written in the web widget and look in the Knowledge Base and give the answer? As opposed to having to create answers and intents etc. 

Thanks

Fiona

What do I need to do to exclude mobile users? 

Visitor platform > does not contain > ios

Visitor platform > does not contain > android

That doesn't seem to work... what should I be doing? Thanks

The reporting is very bare bones at the moment - we don't know common paths people are taking through the "answer" and what people are typing in or clicking on throughout the interaction. When is more detail planned for this dataset? I've seen lots more robust reporting in other similar software so hoping it's just because it's fairly new? Thanks