AI can transform how your workflows handle complex, nuanced tasks that traditionally required human judgment. The action below lets you integrate AI directly into your stories, whether you need to analyze unstructured data, generate content, make context-aware decisions, or create interactive experiences for users. Instead of rigid, rule-based logic, AI brings adaptability and reasoning to your story, allowing your workflows to handle ambiguity and respond intelligently to a wide range of scenarios.
AI Agent action
The AI Agent action brings the power of AI to your stories. It uses a connected language model to analyze text, summarize information, or turn into an AI chat interface for your users to interact with.

Visual of the AI Agent action. It is identifiable as a yellow tile on the storyboard.
What it does: Empowers workflows with AI-powered, adaptable decision-making, capable of analyzing data, taking action, or conversing with users based on your instructions.
When to use it: When a task involves reasoning, summarizing, multi-step logic, or interacting with end users in a guided, dynamic way.
How it works: You define the system instructions, a prompt, and connected tools. Then the AI Agent action uses your chosen language model to interpret those inputs and autonomously carry out the task in either Task or Chat mode.
AI Agent action modes
Task mode
Task mode is designed to uplift your event data. In this mode, the AI Agent action operates autonomously, initiating, reasoning, and responding to a provided prompt, without human interaction. It acts like a monologue, thinking through a task and executing steps using any Tools or Custom Tools it has access to. This is ideal for back-end workflows where you trust the AI Agent action to complete tasks independently.
💡 Real-world example: The AI Agent action transforms a raw internal changelog into customer-facing release notes, written in a user-friendly tone.
Chat mode
Chat mode enables interactive, AI-powered page experiences for end-users. Builders can create customized chat interfaces that allow your end-users to engage directly with the AI, which is guided by the configuration set for the AI Agent action. This mode is best suited for collecting information, guiding users through a process, or delivering personalized responses. This is useful for stories that offer support bots, contact forms, or knowledge assistants. Chat mode also supports Tools and Custom Tools for richer functionality.
💡 Real-world example: Employees interact with an AI Agent action that quizzes them on phishing emails or educates them on safe practices through a gamified conversation.