Call an Agent is an Architect journey element that lets you embed AI reasoning directly in a journey. You write an instruction in plain language, and at runtime it assesses each user's context and returns a structured result you can use for routing, personalization, and profile enrichment. It uses AI credits and is available in standard (non-transactional) journeys.
Call an Agent stays in Architect, and its full documentation lives there. See Call an Agent for configuration, outputs, limits, and analytics.
In this article:
Call an Agent vs. AI Decisioning vs. Decision Agent
Call an Agent, AI Decisioning, and the Decision Agent all bring AI into your journeys, but they do different jobs. Use this table to pick the right one.
Name | What it is | What it does |
|---|---|---|
An Architect journey element. | You write an instruction, and it returns one structured answer per user that you can branch on, personalize messages with, or save to the user profile. It doesn't learn over time, and it doesn't pick between channels, send times, or content variants on its own, only when your instruction asks it to. | |
The concept behind the Decision Agent. | Explains how per-user decisions on content, channel, and time work, and how they learn from each user's reactions. | |
An Architect journey element where Decisioning lives. | It learns per user and decides which content variant, which channel, when, and whether to send at all. |
Choose Call an Agent when you want AI to classify, score, or write something from a user's data. Choose the Decision Agent when you want each send decided per user, with learning over time.