AI Classification is a noteworthy feature that enables you to leverage artificial intelligence to analyze message content and classify messages. This involves sending message data, such as headers and body content, to a third-party AI provider (or processing it with a local AI model) for analysis. Then, based on that analysis, the message can be assigned a classification, or category, such as LEGITIMATE, PHISHING, COMMERCIAL, SPAM, PII_DETECTED, or the like. You can set rules to determine which messages will be analyzed and what actions will be taken based on the resulting AI classification. If your organization's policies permit handling data in this way, this feature can offer significant benefits, such as:
•Advanced Threat Detection — Identify sophisticated phishing attempts that traditional filters might miss.
•Sensitive Content Identification — Detect messages containing Personally Identifiable Information (PII) or other sensitive data.
•Improved Filtering — Filter unwanted messages (e.g., unsolicited commercial emails) with greater accuracy.
Configuring AI Classification
AI Classification is configured from the following pages:
Models — Use this page to manage the list of AI models that you will use to analyze your selected messages. You can add, edit, or remove models, and view their configuration details such as name, endpoint URL, AI profile, timeout, and API key.
Prompts — Create and manage the prompts that will be sent to your selected AI model when a message matches a given rule.
Rules — This page is where you will create the rules to determine which messages to analyze, which prompts to send, and what to do based on the resulting classification assigned to the message.
