AI Actions are automated tasks that allow you to test and monitor large language models (LLMs). These actions are designed to detect vulnerabilities, enforce policy compliance, and uncover risks—without requiring manual effort.
- There are two types of AI Actions:
- AI Event-Driven Actions
Triggered in real time by specific events, such as API calls, findings, or user interactions. Ideal for responsive analysis and dynamic risk detection. - AI Scheduled Actions
Run automatically at defined time intervals (e.g., every 15 minutes). Can be used for continuous or routine scanning.
Action Modes
Each AI Action can be created in one of two modes:
- Custom Actions
Define the action and connect your infrastructure (e.g., AWS Lambda or a webhook). Custom actions give you complete control over the inputs and outputs of the analysis. - Managed Actions
FireTail provides out-of-the-box integration. These actions use prebuilt probes to automatically test for issues like hallucinations, content injection, jailbreak attempts, and more.
Learn more:
