AI Fields

AI Fields are custom attributes generated from your warehouse data using AI. They transform hard-to-activate signals — product affinities, behavioral patterns, weather readiness, predicted intent — into structured fields you can use in segments, personalization, and campaigns.

Getting started

You can create AI Fields through the Data Agent by describing what you want in natural language, or from within a Project's workflow.

1. Describe the attribute you want (e.g., "Score each contact on their likelihood to purchase winter apparel")
2. The Data Agent analyzes your warehouse and proposes the field logic
3. Review the proposed field — including logic explanation, SQL, and sample values
4. Approve the field to create it
5. Choose an inference schedule: one-time or recurring at a frequency you set

📘

Created through conversation

AI Fields are built through the Data Agent chat interface. Describe what you want in plain language — no SQL or data engineering required.

What AI Fields do

• Extract insights from unstructured data — Turn product reviews, catalog metadata, and behavioral logs into actionable attributes
• Predict customer behavior — Build inference models that score contacts on likelihood to purchase, churn risk, or category affinity
• Stay fresh automatically — AI Fields support one-time and recurring inference schedules, so computed attributes update on a cadence you choose
• Integrate into your existing workflows — Use AI Fields anywhere you use contact attributes: segments, journeys, flows, and channel actions

AI Field detail page

Each AI Field has a detail page showing:

Managing AI Fields

From the AI Fields index, you can:

• Search and filter to find specific fields
• View distribution charts for any field
• Archive fields you no longer need — archived fields stop refreshing but can be restored
• Track dependencies — see which other AI Fields or data sources a field relies on

The "Show Only AI-Generated Content" filter on the content index page helps you find templates and content blocks that use AI Fields.

Inference models

AI Fields can be powered by inference models that predict customer behavior based on historical patterns. Inference models support:

• One-time inference — Run the model once to generate field values
• Recurring inference — Set a schedule to keep predictions fresh as new data arrives

When updating an inference model, a SQL comparison view shows what changed between the previous and updated versions.

Availability

AI Fields are available to select organizations. Contact your account manager for activation details.