Unanswered questions

I am finding that when I review the tickets that Knowledge co-pilot is basing it’s new article suggestions on, they are often completely different topics to that of the suggestion. When I first chose to skip a suggestion such as this I was presented with a feedback form to explain my reasoning, however now there is no form and I just see a toast notification saying ‘Recommendation declined: Your feedback helps us improve recommendations” - however I haven’t given any feedback as there is no longer an opportunity to. 

Can organizations define which data sources Knowledge Copilot uses when generating responses, and are there controls available to prioritize or restrict specific content repositories?

is Oauth token expiration for oauth using client credentials grant type also? I am trying to create a new OAuth client using client credentials to test token expiry and obtain new tokens. But get not a valid grant type error. Is the grant type restricted to only one oAuth client?URL used is url = "https://gsmls.zendesk.com/oauth/tokens”If i use the existing Oauth client to get token  get below error“{"error":"unauthorized_client","error_description":"The authenticated client is not authorized to use the access grant “

(New to Zendesk :)) We are bringing a particular assignment process into Zendesk. Our agents are assigned to clients individually and rely on a “Show Name" field to ensure correct work is being accomplished, per show. Our agents do not have faith our clients can consistently write their show names in manually (they are probably right) and are looking for something to automate the process so the correct Show Name is appearing on the ticket for work in our system. We are looking at the use of Organization Fields. “Show Names” field would house their past/current/future show names. We also have a written text field “Show Name” that is exposed to the End-Users. We cannot expose all of our clients show names, due to privacy. Is there any way to automate the "Show Name” field into the ticket for end-users to select (based on which Organization they are in)? Or is there a way to automate the written field to match that internal Show Names field via tags and triggers or Action Builder?  Thank

Hi allI’ve read and re-read the Action Flows articles and tried to make some basic ones of my own but I just don’t understand what I’m doing wrong or what all the technical terms mean. I’m not a developer, I’m an admin trying to build basic things like “If a ticket has a specific tag added to it, add this task list to it” but I just can’t figure it out. The inputs, variables and all the other things are so complicated to understand.I don’t see an Academy course for Action Flows and all the videos I can find that talk about it are very high level and don’t explain everything that I’m seeing. Is there any content I’m missing or can an Academy course be made for this? I like to think I’m at least of average intelligence but I just can’t wrap my head around Action Flows!Thanks!

Hi, is there a way to modify this system action, I don´t want see call transcript in Ticket.Thanks.  

What were your biggest takeaways from Zendesk Relate? What questions do you still have?Join us as we bring the conversation home from Zendesk Relate with me, leader of the Public Sector User Group, and special guests Lezeth and Sydney21 from Zendesk's Customer Success team.Together, we'll explore:AI as an assistant and what it means for public sector teams The biggest themes and innovations from Relate What's on the horizon for Zendesk and customer experienceWe'll also open the floor for our quarterly Wisdom Exchange, an interactive Q&A where you can bring your challenges, share what's working, and learn from peers and the Zendesk Customer Success team.💬 We'd love to tailor the discussion to what matters most to you.Drop your questions in the comments before the event. Whether you're curious about AI, new product capabilities, best practices, or how other public sector organizations are approaching customer service, we'll do our best to address them during the session.We can't wai

Hi,I'm looking for a way in Zendesk to group edit and reorder macros. We have over 500 macros in our account, and doing it manually takes a lot of time and is tedious. Is there a way to fasten this process?

Hi, we are trying to connect our AI Agent to a custom crm api connection that we created within Zendesk, but the current documentation seems to reference how it was done before the merge of Advanced AI Agents into the base AI. Does anyone know how this is currently connected?  Thanks in advance John

We just got access to the full Zendesk AI and I’m playing around and seeing what it can do. I would like to have a custom agent that checks all incoming tickets and sets the priority as urgent if the content mentions needing to cancel an order or update an address for an order. Before I get to that, I made a simple test agent to test the mechanics but I can’t get even that to work.  My instructions are: “If a ticket is created and the end user mentions pink elephants in the comments, assign the ticket to an Admin.” and I made a ticket mentioning pink elephants but the ticket is just sitting there. Do I need to do something else to the custom agent? What am I missing?  Thanks!

I am not getting the right result- only 1 ticket is creating when I have multiple mailboxes on the email .  I have a support ticket open but since this is an EAP I’m also joining this group.I am curious if anyone else has experienced this problem?  

The custom agents correctly analyze PDF files from tickets. Although if a PDF file contains form fields which are filled, these form fields are not detected correctly. The AI agent thinks the form fields are all empty although they are filled.I think there is a transformation missing before you forward the file to the LLM in the background. If you would transform the PDF file into a picture first, that should not be a problem anymore.Real world examples can be found in Zendesk Support Ticket #14916377

I’m scanning through the recommendation from Admin Copilot and there are a number of “Create an article” suggestions. These are recommendations that I create articles for FAQs for which we already have articles. And when I click in the “Related tickets” for the recommendation, it’s quite clear that the AI Agent (Essentials) has replied appropriately to the end-user’s request based on the existing Help Center articles.Our Help Center is 98% locked down - the only 2 anonymously viewable articles are “How to Use this Support Site” and “Legal Notices”. Everything else requires authentication, which is required by our InfoSec team due to the subject matter in our Help Center. Is Admin Copilot basing its recommendations solely on anonymously viewable articles? If so, it’s basically useless for us, and in fact, a distraction (since most of its recommendations are to create articles that exist).

For all calls, we can´t see AI Agents reasing so use-case debug is hard. 

I am trying to add a BSAT survey to the end of the call and it’s not working - the reply is there in the list but how do I add it so that it actually plays at the end of the call?

Hi,the call transcript in log, only show objects, where the log in ticket is successfully.  

I am trying to prepare for the end-of-life of AI Agents-Essential, and since we are Suite Professional, not Suite Enterprise, I have to do this in my production environment. So the risk of breakage is very high. I’ve built a set of automations and Agent SOP around the AI Agents-Essential behaviors and I cannot find sufficient documentation on the new AI Agent email behaviors to have any idea how to make things work the same way.For example - I have triggers for the ar_suggest_true and ar_suggest_false tags being set on a ticket. to guide my Agents? When a ticket is tagged ar_suggest_true, the Agent reviews the AI Agent’s response and unless it’s clearly something they need to manually address, move the ticket to a custom Deferred status, taking no further action unless the end-user indicates that they still need help. Conversely, a ticket tagged ar_suggest_false gets priority because no response has been sent to the end user.Do these tags still exist with the new AI Agent? Is there som

I am trying transfer a live call with the voice agent to a live human agent as an escalation flow, but it keeps failing - the caller says i’d like to speak to a person, and its say ok transferring you now, but then the caller hears  “no greeting available” 3x and it disconnects - and yes, there are greeting dialogues entered- can you help me sort this out?

Why does the voice agent only speak in American English?   We are in Ontario Canada and the Voice AI will often say that they will only support in American English - look at this transcript:    I’m here to help in American English only. How can I assist you today?  How do you change that?

Is there a way to train the voice agent to say words or brand names in a specific way?  

Any one else getting the comment in the transcript that they only support in american english?

After testing the Voice AI Agent I had some feedback to share, please see below:Per the welcome message: “Agent: Hi. You're speaking with an AI assistant. This call may be transcribed by our phone service provider for quality and training purposes.” Is it possible to personalise this welcome message? After mentioning that “I’m unable to connect to our Sandbox”, the answer the Voice AI Agent provided felt like a speed run and it was difficult to follow. Example: “Agent    I'm sorry to hear that. Let me take a moment to look up some guidance on Sandbox connection issues. Please hold on. Thanks for your patience while I dig into this for you. It's important to double check your Sandbox network settings, your API key, and that you're using the right regional endpoint.” Is it possible to slow it down from when it responds with “Please hold on” followed by “Thanks for your patience while I dig into this for you.” After this last statement, “Agent: Alright. I'll get you over to a person who

Hello! I’m working on setting up some advanced AI agents right now for email. We have patients & staff both send questions to the same channel. Ideally, I’d like my AI agent to only respond to questions from patients, not from staff members. However, although I’ve set up instructions & use cases for this, it continues to just respond to every question during testing. Does anyone have suggestions on how I can get it to automatically send questions that don’t pertain to set up use cases directly to live agents?

I'm pretty sure that I have a custom agent which is using a knowledge article which the agent is not linked to.I expected that only knowledge articles that are actively linked to custom agents are used although this agent is mentioning guidelines from another articleI guess this is wrong?

Hello. Following this announcement https://support.zendesk.com/hc/en-us/articles/10955445787546-Announcing-outbound-calling-restrictions-by-agent-group-for-Voice, it is now possible to configure which groups are authorised to make outgoing calls by line. Is it possible to apply the same settings to external numbers? (which are, in fact, only used for outgoing calls)