Agents

Agents are the foundation of AI Decisioning. Each agent defines your audience, messages, and goals, and automatically optimizes campaign performance over time.

Learning objectives

After reading this article, you’ll know how to:

• Create a new agent
• Configure your agent
• Add and manage messages
• Monitor and manage active agents

Overview

An Agent in AI Decisioning combines your audience, messages, and goals into a single adaptive campaign.

Agents use reinforcement learning to decide which message, timing, and channel will drive the best outcome for each user. They operate continuously, learning from real user outcomes such as clicks, purchases, or sign-ups.

Each new message helps the model understand which creative and timing combinations perform best for different audiences.

Create a new agent

1. Go to AI Decisioning → Agents.
2. Click + Add agent.

   

3. Enter a name that reflects your campaign’s purpose, such as Win-back customers or Subscription renewals.
4. Choose a target audience from Customer Studio → Audiences.
5. (Optional) Add a holdout group to measure incremental lift (for example, 20%).
6. Click Add agent.

Configure your agent

After creation, click your agent to open the Configuration tab.

From here, you can set audience eligibility, messages, goals, Smart Suppression, and scheduling preferences.

Step 1: Set audience eligibility

This section shows the audience your agent targets and any experimental setup, such as a holdout group.

Step 2: Add and manage goals

Goals define what your agent optimizes toward.

Each goal represents a measurable event (like a purchase or click) and includes a priority level—helping AID decide which outcomes matter most.

To add a goal:

1. In your agent’s Configuration tab, under Goals, click + Add goal.

   

2. Configure the goal.

   • Select an event model (for example, Purchase event, Viewed Product, or Redeemed offer).
   • (Optional) Add a filter to refine the event, such as Performed → Where property is campaign = Summer Sale.
   • (Optional) Select related collections (for example, Live Offers, In-stock Products) to attribute conversions to catalog items.

   

3. Click Continue to move to the Impact step.

   • Choose whether to include this goal in decisioning or track it for measurement only.
   • Select a classification:
     • Best — Primary success metric
     • Very good / Good — Positive supporting outcomes
     • Bad / Very bad / Worst — Negative outcomes such as Unsubscribe
   • (Optional) Add a weight column to scale results by value (for example, Price or Order Value).

   

4. Click Continue to finalize.

   • Enter a clear, descriptive goal name (for example, Redeemed offer).
   • Click Add goal to save.

   

Step 3 (optional): Configure scheduling

Use the Scheduling panel to control how often and when your agent sends messages.

Step 4 (optional): Enable Smart Suppression

Smart Suppression limits low-impact sends using your agent’s learning data.

It predicts which messages are most likely to drive incremental conversions and suppresses the rest.

1. In Configuration, scroll to Smart suppression (optional).
2. Toggle On.
3. Adjust the Only send top [%] slider.
4. Choose a goal metric to optimize for.
5. Review the performance curve once enough data is collected (typically after 2 weeks).

Step 5 (optional): Advanced settings

Use Advanced settings to connect your agent with your organization’s downstream campaign tracking.

Monitor and manage agents

Once your agent is running, open the Overview tab to review live performance and experiment results.

The Overview includes several key panels:

Use this view to monitor how your messages are distributed, which goals are performing best, and how holdout results compare to treatment performance.

Messages

Messages define the creative variations an agent can send. Each message connects to a destination (such as Braze, Iterable, or Salesforce Marketing Cloud) and can include multiple variants for experimentation.

Agents evaluate messages continuously to determine which variant, timing, and channel perform best for each user.

Add a message

1. Open an agent and go to the Messages tab.
2. Click Add messages.
3. In the Add messages window:
   1. Select a channel and platform (for example, Email via Iterable or Salesforce Marketing Cloud).
   2. Select or create an automation identifier to reference the message in your connected destination.
   3. Enter a message name that clearly describes the message’s purpose (for example, Welcome offer – email or Winback discount).
4. Click Add messages.

Each message appears in the message list, where you can review its status, number of variants, and applied tags.

View and manage messages

The Messages page provides a centralized view of message configuration, usage, and performance for an agent.

From this view, you can:

• Review message status (Enabled or Draft)
• See the number of variants per message
• View applied tags at a glance
• Search messages by name
• Filter messages by status

Use the table controls and filters to quickly locate messages and understand how they are configured before making changes. Each message includes three views to support different workflows:

Use these views together to validate message setup, diagnose issues, and understand how messages perform over time.

Manage messages at scale

AI Decisioning supports two bulk workflows for managing messages:

• CSV upload for adding or updating message content and metadata
• Bulk actions for applying message guardrails consistently

Use CSV upload for content and metadata changes, and bulk actions for guardrails and delivery controls.

Bulk upload and export messages (CSV)

Use bulk CSV upload to add or update messages in an agent at scale. This workflow is best for structured, repeatable updates that are easier to manage in a spreadsheet.

What you can manage with CSV upload

Using a CSV file, you can:

• Add new messages to an agent
• Update existing messages
• Add or modify:
  • Message content
  • Variables and variable options
  • Message- and variant-level tags

What CSV upload does not support

CSV upload does not support message guardrails, including:

• Eligibility filters
• Send limits
• Campaign attribution

Apply these settings in the product UI using bulk actions.

Upload messages with CSV

1. Go to AI Decisioning → Agents and select an agent.
2. Open the Messages tab.
3. Click Add messages, then select Bulk upload with CSV.
4. Download the provided CSV template.
5. Edit the template with your updates.
6. Upload the completed CSV to apply changes.

Apply message guardrails in bulk

Use bulk actions to apply message-level guardrails to multiple messages at once.

Supported bulk guardrails

You can apply:

• Eligibility filters
• Send limits
• Campaign attribution values

Apply guardrails in bulk

1. Go to AI Decisioning → Agents and select an agent.
2. Open the Messages tab.
3. Select one or more messages.
4. Click Actions.
5. Choose one of the following:
   • Add eligibility filters
   • Add send limits
   • Add campaign attribution
6. Configure the settings and apply them.

Troubleshooting

What’s next

• Smart Suppression: Control send volume based on predicted impact →
• Tags: Add and analyze message tags →
• Insights: Measure agent and message performance →