As previously announced, Zendesk is simplifying the packaging of our AI agent functionality and expanding access to our most advanced, agentic capabilities across all Zendesk Suite and Support plans.
This article provides migration guidance for customers who are currently using the following AI agent functionality and need to transition to the new AI agents experience:
- AI agents - Essential
- Legacy AI agent functionality (Bot builder, answers, and intents in AI agents)
- Default messaging responses
This article contains the following topics:
Overview of the change and migration
Between May 11, and June 12, 2026, Zendesk is rolling out our new AI agent packaging model. As part of this change, the distinction between the Essential and Advanced levels of our AI agent functionality is being removed. Going forward, all customers have access to the agentic AI–powered functionality that was previously offered only on AI agents - Advanced.
On August 31, 2026, Zendesk will stop technical development, except for critical bug fixes and supporting breaking changes, for the following features. These features will then be removed from the product in December 2026.
- AI agents - Essential
- Legacy AI agent functionality (Bot builder, answers, and intents in AI agents)
- Default messaging responses
This article includes guidance to help you transition to the upgraded AI agent experience before August 31, so you can avoid any potential disruptions to your customer support.
Migrating an essential AI agent
AI agents - Essential was a previous level of AI agent functionality designed for quick, self-service adoption, allowing you to create generative AI agents that answered customer questions based on content from your knowledge sources.
If you previously created an essential AI agent, you can replicate the same functionality by creating a new AI agent in the new AI agents experience. To get started, see Creating an AI agent to automatically resolve customer issues.
Performing the creation flow described in the linked article results in an AI agent that’s capable of responding to your customers with AI-generated responses based on the knowledge sources you connect to it. This mimics the functionality of AI agents - Essential without requiring you to perform any of the additional configuration required to power more complex workflows.
Migrating legacy AI agent functionality
Bot builder, answers, and intents in AI agents were pieces of legacy AI agent functionality that allowed you to create custom answer flows to address customer questions.
If you previously created an AI agent that made use of any of these pieces of functionality, you can replicate the same functionality in the new AI agents experience.
The table below describes how the legacy functionality maps to the new AI agents experience.
| Concept | Legacy AI agent functionality | Equivalent functionality in the new AI agents experience |
| The interface where you create scripted conversation flows that determine how your AI agent responds to customers | Bot builder | Dialogue builder |
| What the scripted conversation flows are called | Answers | Dialogues |
| The mechanism by which an AI agent understands what a customer is asking about and connects them with the right conversation flow | Intents | Use cases |
To recreate a legacy AI agent in the new AI agents experience, follow the instructions in Getting started with AI agents. As you do, pay particular attention to the following steps:
- Step 4.1: Create use cases to identify customer requests
- Step 4.2: Create generative procedures or dialogues to control responses
As you work through these steps, it may be helpful to first generate a list of your current answers and intents. That way, you can create corresponding dialogues and use cases that cover the same information.
Additionally, to help you as you create your dialogues, the following table shows you which step types in the bot builder map to which block types in the dialogue builder.
| Step type in bot builder | Corresponding block type in dialogue builder |
| Send message | AI agent message |
| Present options | Customer message |
| Show help center articles | Generative replies |
| Add carousel | Carousel |
| Ask for details | AI agent message that presents a form template |
| Ask if question resolved | Customer message that asks if the question was resolved |
| Make API call | API integration |
| Transfer to agent | Escalation |
| Branch by condition | Conditional |
| Add business hours condition | Availability |
| Link to another answer | Link to |
| Set variable | Any block type with an added action that sets a conversation parameter |
Migrating a default messaging response
The default messaging response was the previous way to configure the first message sent to a customer when they launch the Web Widget. This response:
- Includes a basic greeting, a request for more information, and a message letting the customer know they’re being connected to a human agent.
- Can also be customized based on your business hours and the customer’s authentication status.
If you previously configured a default messaging response on any messaging channel, you can replicate the same functionality using an AI agent instead. See Workflow recipe: Using an AI agent to collect customer info and immediately escalate to a human agent.