AI

We’ve started setting up an AI Agent via the Messaging channel for our help centre and trying to tailor it with some basic instructions however despite best efforts, it doesn’t seem to be takingWhen asking if AI Bot was helpful have created the following instruction to try and account for a customer typing yes instead of clicking the yes promptIf the customer types Yes in response to being asked if a reply was helpful then wrap up conversationHowever despite phrasing in a variety of ways, the instruction is not being followedAny suggestions?

With the changes coming to make Advanced AI Agent features available to all customers I am a little in the dark of what that means for existing customers. Are we still required to pay for a seat for the add-on? Keen to hear the views from other Advanced AI Agent customers and if you’ve heard anymore on this?

I know that these two are no longer distinct technically but reading the documentation it isn’t super clear to me if there’s actually a significant change as Zendesk would have you believe. I can see that the upgraded AI can access API’s, and that might be something that would be a game changer as I’ve just started messing around with managing our help center via API, but if anyone has done that already, I’d love to hear examples of how you’re using that. 

Hi team, we use Zendesk for ticketing and the help center. We use gainsight for community. Can we leverage our community for Zendesk agentic AI and copilot?

Today I got a 2nd email announcement about the coming end-of-life for AI Agents-Essential. This email notes that the changes are rolling out starting April 27 (i.e., 2 days ago). But if you link to the announcement post, you’ll note that the rollout has slipped a month (to May 25-June 12) with no change to the end-of-support/end-of-life dates.The post also notes “In the coming months, we’ll share detailed timelines, transition plans, and guidance to help you transition to the upgraded AI agent experience.” (emphasis added). Those details, plans, and guidance should be in place now. The schedule has barely 2 months from the end of the rollout window until the end-of-support date.We have a Professional instanc

Let’s talk about Copilot Ticket Summaries!I didn’t really want to talk about them. In fact, we already did talk about them, tried them, and decided not to buy them. Then you decided to make it weird by forcing them on everyone as a freemium upsale, in the hopes we’ll love them so much we want to pay a severely discounted price for them for a short time before the AI compute bill comes due for us all.  How do we opt out of having this unwanted and already-rejected feature enabled for our account? In advance, if you please.I don’t want to have to wait for them to be switched on to switch them off. And if I may say so: This is a pattern of feature rollout with Zendesk

🎟️ Your way to Denver: 10 Discussions, 10 Relate TicketsWe want to help you get to Relate while connecting with the people navigating the same CX hurdles as you. This topic is one of ten. Here is how to win your seat:Engage: Pick any topic that sparks your interest and jump in! You only need to participate in one to enter, but feel free to join as many as you like to increase your odds.   The Bonus: Update your community profile with your info for an extra opportunity to win.Winners will be announced the latest on Thursday, May 14. Good luck! 🍀 TOPIC 4: Leading in the AI era 🚀

 🎟️ Your way to Denver: 10 Discussions, 10 Relate TicketsWe want to help you get to Relate while connecting with the people navigating the same CX hurdles as you. This topic is one of ten. Here is how to win your seat:Engage: Follow  to the  Group and conversations in the Relate Hub that interest you most. Increase your odds: Every discussion you join increases your chances of winning one of 10 complimentary tickets.   The Bonus: Update your community profile with your info for an extra opport

🎟️ Your way to Denver: 10 Discussions, 10 Relate Tickets We want to help you get to Relate while connecting with the people navigating the same CX hurdles as you. This topic is one of ten. Here is how to win your seat:Engage: Pick any topic that sparks your interest and jump in! You only need to participate in one to enter, but feel free to join as many as you like to increase your odds. The Bonus: Update your community profile with your info for an extra opportunity to win.Winners will be announced the latest on Thursday, May 14. Good luck! 🍀 TOPIC 6- MEASURING AI

ProblemWhen having extensive flows I can’t easily connect multiple templates together in one use case/flow.What I would like.User ask question (case)Template A - Authorize user and create temporary access token for that user. Template B - API call - show list of entities and select entity (`/api/v1/entities/`) Template C - API call - show list of entities and select entity (`/api/v1/entities/id/items`) Template D - API call - present solution for entity item  What happens now;Case; I have problem with item.Set `destination` parameter (D) Link to template A: On success → destination === D→ link to template B Template B: On success → destination === D → link to template C Template C; On success → destination === D → link to template C Template D; Answer question for user.

Today, when working with Zendesk AI Agents and JSONata, it is possible to retrieve and display data from APIs (including large arrays), but there is no way to dynamically reference an array position based on user input during the conversation.A very common use case is displaying a numbered list to the user, for example: 1 - Option A 2 - Option B 3 - Option C ...The user then replies with a number (e.g., “84”), and the expected behavior would be to map this input back to the corresponding item in the array and retrieve its attributes (such as an ID).However, today it is not possible to perform something like: var_array[user_input - 1].idThis creates a significant limitation when building scalable conversational flows that rely on dynamic data from APIs.Why this mattersMany APIs return large and dynamic datasets (100+ items, growi

We have a small pilot users testing with the AI agents.  They are having conversations with the AI agent in the help center using the chatbot.  I was expecting to review their conversations in the “View unresolved conversations” in the AI agent settings.  I only found conversations 8 days ago (April 1 and before).  Nothing between April 2 and April 8. Is there a setting that I need to configure?

I am trying to setup an automation for tickets that are not assigned for two hours.  My research led me to two settings in setting up the automation. Meeting all of the following conditions: Ticket: Hours since assigned and my two choices are (business) Greater than(calendar) Greater than I've tried both and neither is working.  I've followed the automation setup instructions in the zendesk online documentation so I think the rest of the settings are correct.  But the “internet” told me that the two Greater than conditions could be problematic so I tried one then the other and neither is working.   Can you provide some direction?  Thank you.

I see your announcement where you are forcing AI upon us.Will there be a way to turn it off as we do not want to be sharing our info with Microsoft or using this AI slop. 

I’m facing an issue with Zendesk AI intent detection and webhooks. I have AI intent detection enabled, and the intent is successfully detected on the ticket (I can see the system tags and the intent/confidence in the ticket events).I am trying to send the detected intent to an external system via webhook. My webhook body looks like this:{"ticket_id":"{{ticket.id}}","action":"{{ticket.ticket_field_33209525892626}}","intent":"{{ticket.ticket_field_option_title_33190930229522}}","tags":"{{ticket.tags}}","intent2":"{{ticket.ticket_field_33190930229522}}",}The problem is: Sometimes the webhook receives the correct intent. Other times, the webhook fires but the intent field is empty. In the ticket events, I can see that AI intent detection My questions: What is the recommended way to ensure the webhook only fires after AI intent detection is completed? Is there a guaranteed even

I am trying to find some system for setting up an AI based prescreener for our talk system. I reached out to PolyAi, but we apparently do not meet their call number requirements. Are there other options for including voice based AI into the system?

Context: The tag ai_agent_automated_resolution is automatically added when a ticket is marked as resolved by a requester.Problem 1: It is added even if, in the meantime, the requester or an agent reopens the ticket and public replies are exchanged. This happens regardless of whether the ticket is resolved or not. Problem 2: It is not removed if, after resolution, the requester or an agent reopens the ticket and public responses are exchanged. This is true even if the ticket is set to Incident Type and Resolved by a Problem ticket (the tag should be automatically removed either when the ticket is reopened or when the next public response is made by an agent).Underlying problem: tickets are considered resolved by AI even though the final response is provided by a human agent. = AI resolution is counted in the automatic resolution counter (unless I am mistaken).Solutions: change the criteria for adding the ai_agent_automated_resolution

Hey Zendesk Community, Artificial Intelligence (AI) is everywhere these days, and I’m sure your company is talking about or working on implementing it in one way or another. It’s a big topic, and one we all need to be keeping current with, which is part of why we created the AI discussion topic. To get the conversation going here, I thought it might be helpful  to start by sharing how we're each  using AI at work, or how our companies are starting to implement it. Sharing will help inspire everyone to be thinking about AI , and hopefully we can learn from each other's experiences.I’ll start. I’ve been using ChatGPT to help me summarize content within a character or word limit for social media. ChatGPT has also been a great resource for post suggestions within this AI topic in particular.  For example, I was able to ask ChatGPT to extrac

Anyone here using AI Voice Agents integrated with Zendesk? I’d love to hear about your experience — how well it works, whether it’s worth the investment, and which platforms you’re using. I’m currently considering CloudTalk’s AI Voice Agent. Has anyone tried it and can share feedback (setup, handoff to agents, ticket creation, etc.)?

See my screenshot. Only the "Everyone" option gives access to the AI messaging tool to train on. 

Please let me know how to do settings for using Zendesk AI chatbot correctly. We applied to Zendesk and got the feature to provide AI chatbot to our customers today. The widget was displayed on our Guide, but we thought it was not working correctly. Because the bot said the following message in Japanese. "Sorry, we were unable to answer your question. The following topic may be helpful."Whatever the question, he answers same. How can we get the answer based on our Guide?

I just noticed that conversations between your AI agent and customers that aren't escalated are NO MORE created as READ-ONLY tickets available in Agent Workspace. They are as Open tickets and our agenst can select them.Have you done an update? 

Hi there,Good day I would like to understand how to make the AI Agents that I am building via Ultimate AI dashboard accessible to the end users via the: https://<subdomain>.zendesk.com/hc/en-us page. This seems to be the way: https://support.zendesk.com/hc/en-us/articles/8357757747354-Connecting-your-advanced-AI-agent-to-Zendesk-Chat Can anyone let me know if I am following the right path? Also, it seems that the AI Agent need a configured email / account of its own, is this correct?

I've had a support ticket open 2.5 weeks to get some info on this but since they aren't responding I'll just ask here Has anyone used the detecting customer intent / sentiment and language feature that was introduced?https://support.zendesk.com/hc/en-us/articles/4550640560538-Automatically-detecting-customer-intent-sentiment-and-language   Wondering about its functionality within zendesk to quickly pull the information as to what customers are talking/asking about in their tickets to quickly get an overview of emerging issues etc. It seems like this is something this feature can do but its like getting blood out of a rock to get some factual and accuract data from zendesk support atm

Hi Zendesk.Could you have additional filters for the Merge ticket suggestions so we can set a hard rule to only show merge suggestions if the tickets have same intent and if tickets belongs to same group. Additionally, having options to restrict this feature for certain roles would be great.Thanks