Enable AI Agents

This page explains how to enable AI agents on your Appian environment, including deployment requirements, supported regions, and the steps to activate the feature. AI agents are available exclusively on Appian Cloud—there is no self-managed or standalone deployment option.

AI agents deployment options

AI agents run on Appian Cloud's managed infrastructure and use large language models (LLMs) hosted in supported AWS regions. Appian manages all infrastructure required to run AI agents, including model hosting, tool execution, and agent orchestration.

The following constraints apply to AI agents deployment:

• Appian Cloud only: AI agents are supported in Appian Cloud environments only. You cannot use AI agents in self-managed environments.
• No standalone application: AI agents do not have a separate site or portal. You create and manage AI agents directly in Appian Designer as design objects, alongside your other application objects such as process models, interfaces, and record types.
• No self-hosted model option for AI agents: The LLMs that power AI agents run on Appian's private AI infrastructure. You cannot host the AI agent execution runtime on your own infrastructure.

Prerequisites for enabling AI agents

Enabling AI agents requires the following prerequisites in your environment:

• Supported region or cross-region inference: Your Appian Cloud site must either be hosted in a region that supports Sonnet 3.7 or later models, or be opted in to the cross-region inference feature. See Regional availability for AI agents for the full list of supported regions.
• AI model enabled: You must enable at least one AI model that supports AI agents in the Admin Console. AI agents automatically use the latest enabled Sonnet model.

Enable AI agents

Enabling AI agents on your Appian Cloud site requires you to enable a supported AI model and select an inference profile in the Admin Console. Once the model is active, all developers with appropriate object permissions can create and use AI agents in Appian Designer.

To enable AI agents on your environment:

1. In the Admin Console, go to Integration > AI Services.
2. On the Appian tab, locate a model card that supports AI agents (such as Claude Sonnet 4.5 or Claude Sonnet 4).
3. On the model card, use the Selected Profile dropdown to select an inference profile for your region.
4. Click SAVE CHANGES.

The model card displays an ENABLED status tag when the inference profile is active. AI agents are now available as a design object in Appian Designer.

Verify AI agents are enabled

After enabling a supported model, verify that AI agents are available in Appian Designer.

To confirm that AI agents are enabled:

1. In Appian Designer, open an application.
2. Click NEW and look for AI Agent in the list of available design objects.
3. Confirm that AI Agent appears as a selectable object type.

If AI Agent does not appear, verify that your license tier is Advanced or higher and that a supported model is enabled in the Admin Console.

Regional availability for AI agents

AI agents are available in select AWS regions. If your Appian Cloud environment is not in a supported region, you can select an inference profile to allow processing in a supported region. Selecting an inference profile outside your site's primary region may introduce data latency.

To check whether AI agents are supported in your region, use the AI Feature Model & Region Explorer on the Regional Availability page. Select AI Agents from the Feature dropdown to see which regions and inference profiles are available.

Troubleshoot AI agents enablement

If you encounter issues while enabling AI agents, check the following:

• AI Agent does not appear in Appian Designer: Verify that your license tier is Advanced or higher. AI agents are not available on Standard or Express tiers.
• No supported model available in AI Services: Confirm that your site is in a supported region or that you have selected a cross-region inference profile. If no inference profiles appear, contact Appian Support.
• Model card shows DISABLED status: Select an inference profile from the Selected Profile dropdown on the model card and click SAVE CHANGES.
• "Region not supported" error: Your site is in a region that does not natively support the required models. Select an inference profile that routes processing to a supported region.

For additional help, contact Appian Support.

Feedback