Automated resolutions are the unit of measurement used for calculating and billing your account for AI agent usage.
Paying per automated resolution means that you pay only for customer requests that were successfully resolved by the AI agent, without any escalation to a human agent. Conversations flagged as resolved are also verified by a large language model (LLM), ensuring its accuracy and delivering a true automation rate.
Zendesk provides tools for monitoring and managing your automated resolution usage.
This article contains the following sections:
Related articles:
Understanding how automated resolutions are measured
An automated resolution is counted when a customer’s issue is successfully resolved without live-agent intervention. Automated resolutions are counted per conversation rather than per user. A single user’s visits over multiple channels, browsers, or devices will be considered separate interactions.
There are differences in how and when an issue is deemed resolved, depending on the channel used. This section explains these differences so you can better understand your usage.
- Automated resolutions in AI agents for messaging
- Automated resolutions in advanced AI agents
- Automated resolutions in autoreplies with articles
- Automated resolutions in autoreplies based on intelligent triage
- Automated resolutions in Web Widget (Classic)
- Actions that don’t contribute to automated resolution calculations
Automated resolutions in AI agents for messaging
Automated resolutions are calculated in an AI agent for messaging deployed on a messaging Web Widget, a mobile SDK, and on a third-party messaging channel such as Facebook Messenger, X Direct Message, Instagram Direct, LINE, or WhatsApp.
An automated resolution is counted after 72 hours of inactivity if AI evaluation has confirmed that the AI agent’s response was relevant and the last interaction was one of the following:
- The end user provided positive feedback (“Yes, problem solved”)
- If no feedback is provided, the conversation will be evaluated using AI
- The AI agent shared help center articles in response to the end user’s
request:
- If articles were shared using Article Recommendation or an article step in an answer flow, the end user must have clicked on at least one article link.
- If articles were shared in a generative reply, the end user doesn’t have to click on an article for an automated resolution to be counted.
- The end user reached the final step in an answer flow.
The end user is anyone who makes a request and interacts with the AI agent (referred to as a "bot" in the flowchart below).
Automated resolutions in advanced AI agents
If you have the AI agents - Advanced add-on, automated resolutions apply to both chat and ticket AI agents, and are calculated using the following logic:
-
For chat AI agents: An automated resolution is consumed for any conversation that is considered AI agent-Handled and passes the verification performed by our LLM.
-
For ticket AI agents: An automated resolution is consumed for any conversation that is considered Answered (because a reply was sent) and passes verification performed by our LLM. Adding actions or internal notes only does not consume an automated resolution.
The verification process performed by the LLM evaluates the text of the conversation to ensure that the customer’s request was actually satisfactorily resolved without human-agent intervention. Conversations that don’t pass this verification are not considered automated and do not consume an automated resolution.
Automated resolutions are evaluated at the end of the conversation session duration, which is configurable for a chat AI agent and 72 hours after the arrival of the first message for a ticket AI agent.
Only conversations with the AI agent-Handled or Answered status are evaluated for automated resolutions. All escalations change the status of a conversation to something other than AI agent-Handled or Answered. This means that as soon as a conversation is escalated to a human agent, it can no longer be counted as an automated resolution.
Automated resolutions in autoreplies with articles
If you’re using autoreplies with articles in email notifications or web forms, an automated resolution is counted in either of the following situations:
- An article is suggested to the user, and the user clicks “Yes, close my request” in:
- A feedback prompt on the article page opened via the email notification or web form.
- A feedback prompt embedded in the email notification or web form.
- An article is suggested to the user, and within 72 hours, the user clicks on the suggested
article link and
- The ticket status is marked solved before any user or public agent reply or
- No user or public agent reply has been added to the ticket.
Automated resolutions in autoreplies based on intelligent triage
- An autoreply is added to a ticket using a trigger based on an intelligent triage condition.
- No user or public agent reply has been added to the ticket in 72 hours.
Automated resolutions in Web Widget (Classic)
If you’re using Web Widget (Classic) to deliver article recommendations to your end users, an automated resolution is counted when the AI agent has suggested at least one article via Article Recommendations and the end user has clicked on at least one article preview link or provided positive feedback “Yes, problem solved”.
The conversation is considered unresolved if:
- The user initiated a live chat
- The user submitted a contact form
- The user requested a callback
- The user provided negative feedback (“No, I still need help”)
- The AI agent (referred to as a “bot” in the flowchart below) didn’t understand the request
In the Web Widget (Classic), a session ends after 72 hours of inactivity or when the end user closes the browser or tab.
Actions that don’t contribute to automated resolution calculations
Understanding the default allocation of automated resolutions per plan
All Zendesk Suite and Support plans include a baseline number of automated resolutions based on your plan type. You can increase the number of automated resolutions to avoid exceeding your allotted amount, orpause the AI agent functionality when you reach your limit in order to prevent overage.
If you want to ensure your account isn't consuming any automated resolutions, you can turn off all capabilities related to AI agents.
Default automated resolution allocation per plan
Most Zendesk usage plans include a number of automated resolutions. If you’re not part of a Suite or Support plan or find that your plan doesn’t provide enough automated resolutions, you will be able to purchase more as needed.
The following table shows how many automated resolutions are included in each plan. Light agents are not included in the default allocation calculation. Accounts on all plans have a maximum of 10,000 allocated automated resolutions per year, applied after the new pricing plan takes effect. If you need more automated resolutions, you can add them to your account.
| Plan | Zendesk Suite | Support (standalone) |
|---|---|---|
| Enterprise | 15 automated resolutions/agent/month | 15 automated resolutions/agent/month |
|
Professional Growth |
10 automated resolutions/agent/month | 10 automated resolutions/agent/month |
| Team | 5 automated resolutions/agent/month | 5 automated resolutions/agent/month |
Your allocation of automated resolutions expires annually or at the end of your subscription term (if less than a year) unless you are on a non-standard subscription term.
Adding automated resolutions to your account
You can increase the number of automated resolutions to avoid exceeding your allotted amount. Using more than your allotted resolutions can result in overage charges.
You can add to your automated resolution allotment by purchasing 100 or more automated resolutions ahead of time. Also called committed usage, this approach allows you to raise the maximum number of automated resolutions available to you in advance. Committed usage provides a better per-resolution cost than overage billing (or pay-as-you-go).
If you choose an overage billing (or pay-as-you-go) approach to automated resolutions management, the cost per automated resolution over your allotment will be greater than the cost per automated resolution when you buy a fixed number to increase your allotment. You can prevent overage billing by limiting the number of automated resolutions available in your account each month. Overage is billed monthly, regardless of your subscription terms.
Avoiding automated resolution overages
You can choose how your account responds when you reach your automated resolution limit.
For more information, see Maintaining or pausing functionality when you reach your automated resolution limit.
Finding more information
If you have feedback or questions related to AI agents, visit our community forum where we collect and manage customer product feedback. For general assistance with your Zendesk products, contact Zendesk Customer Support.
13 comments
Viachaslau
Enterprise: 15 automated resolutions/agent/month included. Very generous. $1.00 per resolution with 5,000 resolution tier. This is a dramatic price change for us
4
Maxi Cooper - menze
Hi. Is there going to be a panel where we can review each conversation automatically resolved by the agent?
1
Billy Smillie
Hi, the way we steer our customers using the web widget, we don't offer a ‘connect to agent’ feature and the end of each flow directs to a form. However, this results in every contact appearing as an automated resolution, therefore filling our monthly limit within a few days. Is there anything we can do to assist with this?
2
Trudy Slaght
We have a fair number of customers who contact us on multiple channels at the same time - so they may message us, and call us - then have their inquiry resolved by phone. With the 72 hour no reply being counted as the bot having resolved things, this seems like there will be a lot of resolutions counted that haven't actually been deflected.
Are we going to be forced to disable the chat bot completely to prevent this from occurring? This is a major pricing change when we've actually found that transfers to agents have INCREASED since implementing the article suggestions and yet I see in our dashboard “5” resolutions from yesterday with no insight into how those inquiries were resolved.
The amount of resolutions included in the enterprise plan also does not seem to be a realistic number so I am currently failing to see the benefit here since there is lack of transparency around seeing what was counted as resolved. The lack of response from a customer being assumed to equal a non-transferred inquiry is quite an assumption that is not in line with what we see in our use case.
5
A A
A resolved conversation is when the bot asks if the issue is resolved yes/no? If the client confirms that yes, it is resolved. Then it is resolved.
If a client just leaves a conversation, it doesn't mean that it is resolved. I'm surprised that you're going to charge $1.5 per such conversation.
3
Elina
I agree with A A ! I have just checked our current “resolved” chats, where customers were not transferred to an agent, but did not answer the "YES or NO is issue resolved" question. Most of them were indeed not resolved and customers contacted us again via a different channel or started a new chat. Do I understand it correctly, that those unresolved chats will count as resolved?
1
Keegan
If I understand this correctly, a conversation that a customer indicates as resolved will count towards this, even if no AI generated answer was provided. With only 10 resolutions per agent per month, this is going to push us AWAY from trying to improve the self-serve rate, as it's probably cheaper for an agent to respond to an easy question with a macro than for the bot to answer that question
2
Brandon Tidd
Billy Smillie As I'm reading this - conversations escalated to an agent (by way of a form submission) will *not* count towards the # of resolutions.
Keegan obviously this is very fuzzy math but the logic here is that your human-in-the-loop would cost you more than $1 to touch that ticket.
0
Maxi Cooper - menze
Which is a very US/Europe-centric view, isn't it Brandon Tidd ?
1
A A
An agent can resolve 2000 tickets per month. If salary is $500, it would cost $500.
With Zendesk chatbot it would now cost $2600.
A $1.5 per conversation is viable only for the US/Europe. In our case, we will have to disable the chatbot and look for an alternative solution.
2
Brandon Tidd
Maxi Cooper A A All valid points - as with anything at Zendesk, I would assume that this model will evolve over time based on customer needs and feedback. What I can tell you is that this plan is exponentially better than the first MAU version that we saw floated last year.
0
Bobby Koch
We need an answer here from Zendesk, as soon as possibl.e You cannot charge us for customers abandoning the widget, that is not acceptable.
2
Jeff Curran
Thank you for your feedback and sharing your thoughts with us about the impact of this change. We understand that change can be challenging, and we hope to offer more clarity to address your concerns directly.
From these comments, here is what we’ve heard so far:
1. Price increase and plan limitations: Customers have expressed concerns about the significant changes in pricing and limitations of the new pricing plan, particularly regarding the number of automated resolutions included in the enterprise plan.
At Zendesk, our objective is to provide simple and value-aligned pricing. The introduction of AI agents and our new automated resolution pricing model are designed to reflect both of these goals. We chose automated resolutions because it aligns directly with the value delivered to our customers by Zendesk. Under this model, customers only pay for the tangible value delivered by AI Agents. In contrast to our competitors, we chose to include a starter amount of automated resolutions to ensure that customers can experience the value of AI Agents before any additional payment is required.
2. Transparency and accountability: Users have voiced concerns over the transparency in determining what constitutes a resolved conversation, especially when customers do not explicitly confirm resolution or when they engage across multiple channels.
We are committed to creating a transparent and trustworthy system to define automated resolutions. To that end, customers will have access to two dashboards. The first is a usage dashboard that will track current usage and entitlement, offering real-time insights for planning and billing purposes. Additionally, customers will be able to set a cap on usage to ensure predictability in their costs. The second dashboard provides transcripts of conversations handled by AI agents on the Messaging channel, covering up to the past seven days. In the future, we will provide an audit trail, allowing customers to inspect automated resolutions for accuracy, success, and automation of resolutions.
3. Impact on self-service and support costs: There is concern that the new pricing model may discourage efforts to improve self-service rates, as it might be more cost-effective to have agents handle certain inquiries rather than relying on the AI agent.
Our new pricing model is designed to give customers flexibility to serve their end-users in the most effective way for their business, whether that be through human agents or AI agents via automated resolutions.
4. Global pricing: Some users have highlighted the pricing model appears to be more geared to regions like the US and Europe, raising concerns for users in other regions where the cost-effectiveness of AI-powered support may vary.
We provide volume-based discounts to accommodate the high-volume use of deployments of Zendesk. In instances where our standard pricing does not align with your specific use case, we encourage you to contact your account executive for tailored assistance.
We hope these answers help clarify your questions and provide helpful information in navigating these upcoming changes.
With that being said, we would love to continue the conversation with you! We have opened up a Community feedback post for further comments, questions, and concerns about this change. Our goal is to gather your input in a centralized location where our product teams engage most actively, allowing us to provide you with more prompt and detailed responses.
At this time, we will be closing comments on this article and shifting our conversation to this Community feedback post for further discussion. We appreciate your willingness to voice your concerns and thank for being a part of the Zendesk Community.
0