Communication guidelines in Zendesk Copilot: what does this AI read, and can you turn it off?

Checked on October 28, 2026 by verification chain vchain-1

Whether it is on by default is not yet verified; it can be turned off.

The facts, edition by edition

	All editions
What the AI does	Write “Communication guidelines use generative AI to adapt agent responses to the overall writing style and tone of a conversation, and also allows auto assist to adapt its suggestions accordingly.” “Adapts messages to match your brand voice and follows rules for tone, length, and structure; if not, it still stays consistent with the conversation.” [3] dated copy
Model	Not yet verified
What it reads	Not yet verified
Where the data goes	Not yet verified
Trains on your data	No “These features leverage large language models (LLMs) developed by third-party vendors, which are not trained on Zendesk data.” [4] dated copy
On by default	Not yet verified
Can be turned off	Yes “Turning communication guidelines on or off” “Admins enjoy consolidated, thoughtful feature configuration that lets them control which features are available and to whom.” “Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” “For example, Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” [2] dated copy
Billing	Not yet verified
Feature type	Not yet verified
Frameworks the catalog links to it	Not yet verified

What the AI does: Write “Communication guidelines use generative AI to adapt agent responses to the overall writing style and tone of a conversation, and also allows auto assist to adapt its suggestions accordingly.” “Adapts messages to match your brand voice and follows rules for tone, length, and structure; if not, it still stays consistent with the conversation.” [3] dated copy
Model: Not yet verified
What it reads: Not yet verified
Where the data goes: Not yet verified
Trains on your data: No “These features leverage large language models (LLMs) developed by third-party vendors, which are not trained on Zendesk data.” [4] dated copy
On by default: Not yet verified
Can be turned off: Yes “Turning communication guidelines on or off” “Admins enjoy consolidated, thoughtful feature configuration that lets them control which features are available and to whom.” “Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” “For example, Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” [2] dated copy
Billing: Not yet verified
Feature type: Not yet verified
Frameworks the catalog links to it: Not yet verified

All editions: Yes “Turning communication guidelines on or off” “Admins enjoy consolidated, thoughtful feature configuration that lets them control which features are available and to whom.” “Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” “For example, Copilot AI features are grouped in a centralized AI hub and identified to admins, who have the ability to turn off any feature at their discretion.” [2] dated copy

Linked frameworks will appear once the reference set is published.

No change since first publication.

This fact sheet says nothing about your setup: the free readout, in French for now, reads it in your tools.