Automated resolutionsare the unit of measurement used for calculating and billing your account forAI agentusage. Paying per automated resolution means you pay only for customer requests that were successfully resolved by an AI agent, without any escalation to a human agent.

What's my plan?
All Suites Team, Growth, Professional, Enterprise, or Enterprise Plus
This article describes the automated resolution tiers that were introduced on May 18, 2026.

Automated resolutions are the unit of measurement used for calculating and billing your account for AI agent usage. Paying per automated resolution means you pay only for customer requests that were successfully resolved by an AI agent, without any escalation to a human agent.

Automated resolutions are grouped into tiers that reflect the value the AI agent provided. Your account is automatically credited with a resolution allowance, from which the cost of the automated resolutions is drawn.

Understanding the automated resolution tiers

Automated resolutions are grouped into tiers. These tiers ensure you don’t overpay for straightforward tasks, while accurately reflecting the value of more complex resolutions.

The table below describes the automated resolution tiers.

Tier name Description How this tier is measured
Assisted escalation The AI agent contributed to the interaction before a human agent completed the resolution. This tier does not count against your resolution allowance. The AI agent may have collected some data, authenticated the customer, or provided routing assistance, but ultimately the conversation was still escalated to a human agent to be resolved.
Contained resolution The AI agent handled the interaction to completion without the customer requesting further assistance. This tier does not count against your resolution allowance. The AI agent responded to a customer’s question, and the customer did not do any of the following:
  • Request further clarification.
  • Provide feedback on the AI agent’s answer.
  • Ask to speak to a human.

When the conversation ends, a verification process is performed by a large language model (LLM) that evaluates the text of the conversation to confirm that the customer’s request was satisfactorily resolved. Conversations that don’t pass this verification are considered a Contained resolution.

Verified resolution The AI agent successfully resolved the interaction. The AI agent responded to a customer’s question, and the customer did not request further assistance.

When the conversation ends, a verification process is performed by an LLM that evaluates the text of the conversation to confirm that the customer’s request was satisfactorily resolved. Conversations that pass this verification are considered a Verified resolution.

When a conversation is considered ended depends on the channel it happens on:

  • Email: The conversation ends 72 hours after the last email in the conversation.
  • Messaging: By default, the conversation ends 2 hours after the last message in the conversation, though this can be increased up to 72 hours. For assistance increasing the conversation end time for messaging, contact Zendesk customer support.
  • Voice: The conversation ends immediately upon hangup.
Powered by Zendesk