This page is part of the Customer.io documentation. For the complete documentation index, see llms.txt.

80

AI settings

You’ll find AI settings under Settings > AI. These settings apply across all workspaces in your account.

We don’t use your data to train AI models

We do not use your customer data to train AI models, and we don’t use your users personal data (attributeA key-value pair that you associate with a person or an object—like a person’s name, the date they were created in your workspace, or a company’s billing date etc. Use attributes to target people and personalize messages. and event values) in any of our AI features. You can safely use our AI features without worrying about us using your customer data to train AI models.

Customer.io AI toggle

By default, you and your team members can take advantage of AI-based features in your account.

If you’re not comfortable with members of your team using AI-based features, disable Customer.io AI under Settings > AI. Disabling Customer.io AI turns off all AI features for everybody in your account.

Edit live data

By default, the Customer.io agent cannot edit “live” data, delete profiles, or trigger broadcasts, newsletters, and other messages. This protects you from accidental changes to your Customer.io data and automations.

If you want the agent to make changes to live resources, turn on Allow agent to edit live data. When this setting is on, your agent can modify anything that your permissions allow, including active campaigns and in-use segments. You must be an account admin to manage this setting.

Be careful when working with live data. Things like changing an active campaign workflow can disrupt user journeysTypically, a person’s path through your campaign. If the campaign is triggered by a webhook, then a journey captures the webhook’s path, not a person’s..

This setting does not affect our MCP server or CLI tools. Take care when working with live campaigns, segments, modifying people’s profiles, and so on through those tools.

Gemini safety settings

AI features in Customer.io use Google’s Gemini models. You can configure safety thresholds for content created by our tools from the Gemini Safety Settings section. For a full list of features powered by these settings, see our current functionality powered by AI.

You can set filters for four categories:

• Harassment
• Hate Speech
• Sexually Explicit
• Dangerous Content

For each category, you can choose a threshold ranging from Off (no filtering) to Block low and above (strictest filtering). Learn more about Gemini’s safety settings in Google’s documentation.

Compliance prompt

In your AI settings, you can include a Compliance Prompt to help ensure generated content aligns with other regulatory and policy guidelines not covered by Gemini Safety Settings.

Customer.io MCP

Toggle Customer.io MCP to turn the Model Context Protocol (MCP) integration on or off. When MCP is on, team members can connect AI tools like Claude, ChatGPT, and Cursor to their Customer.io workspaces. See our MCP documentation for setup steps and details.