Custom AI agents
AI-powered

Overview

PREREQUISITES:

You must have an active Sitefinity AI subscription.
For more information, see Sitefinity AI.

This capability is available out of the box in Sitefinity Cloud with version Sitefinity 15.4.8631.

New AI agents framework is provided that enables you to define and create custom AI agents in your Sitefinity backend. You can use your custom AI agents in parallel with the built-in AI agents or independently. The AI agents framework allows custom agents to be configured through system prompts and settings individually, as described below in this article.

Upon interacting with the custom agent, content editors can apply consistent personalized recommendations for Stefinity content, which are displayed in-context during their authoring experience.

Create a custom AI agent

If you want to create and configure a custom AI agent in your Sitefinity backend, you can do so via the AI agents module. Perform the following:

Log in to your Sitefinity backend with Administrator privileges.
Navigate to Administration » AI agents.
On the AI agents screen, click Create AI agent.
The Create AI agent screen opens.
In Agent name, enter the name of the custom agent.
For example, enter Clarity & Readability.
In Enable this agent, you can optionally disable the AI agent by selecting No.
The default setting is Yes.
In Instructions, you define the prompt that is sent to the Large Language Model (LLM) when the AI agent is executed (as per your individual needs). Manually feed your guidelines as no specific format is required. These instructions should guide how the AI agent analyzes the Sitefinity content and performs its tasks.
For multisite setup, under This agent works with..., select the desired option:
- All sites (default option) - use this option if you want your AI agent to work consistently across all your sites.
- Selected sites - use this option if you want your AI agent to work only for the site(s) you select here.
Under For content types and fields..., select the desired option:
- All content types and fields - use this option if you want your AI agent to suggest improvements for all available content types and fields.
- Selected content types and fields... - use this option if you want your AI agent to suggest improvements only for content types and fields that you specify here one by one.
  The agent will analyze all fields of the selected content types, but suggestions will be generated only for the content in the selected (added) fields.
  For example, the Clarity & Readability agent may be configured to suggest improvement only for Description and Content fields of News content type.
In the Agent identity section:
- In Short name, enter a shorter version of your AI agent name.
  The short name is used where space is limited in the UI. For example, you can enter Readability.
  If you do not provide a short name, the Agent name setting is used.
- In Agent ID, you provide an unique identifier for your AI agent (used internally by the AI agents workflow orchestration).
  For example, enter clarity-and-readability.
Click Create.

NOTE: Unlike built-in AI agents, your custom AI agent can be deleted. To do this, on the AI agents screen, click the (Actions) menu for existing custom agent and select Delete.

Use custom AI agents

Once created and configured, your custom AI agent is integrated directly into the Sitefinity content editing experience and is ready to surface AI-powered suggestions for existing or new content items.

When opening an existing content item for editing or creating a new one (such as Blogs, News, and Events), the AI agent analyzes the affected fields and generates different recommendations - according to the configured behavior of the agent.

If multiple AI agents are activated for the same content item (applies to built-in AI agents too), all agents are executed in an orchestrated order and some of the generated AI suggestions may overlap - these suggestions are already aggregated and merged before being surfaced on the UI.

Content editors get a notification icon (Content suggestions) on their active screen indicating the counter of all AI-generated suggestions for the currently open content item.
By clicking on this icon, content editors access the AI-generated suggestions through the Content suggestions sidebar on the screen.

The provided suggestions are actionable and in the sidebar, they are grouped by the individual sections and fields of the currently open content item.

NOTE: No content changes can be applied by the AI agent itself without a human in the loop.

When reviewing the AI-generated suggestions in detail, content editors can perform the following actions available in the Content suggestions sidebar:

Filter the AI suggestions available on the user interface, provided multiple AI agents are configured and enabled in your Sitefinity backend - by clicking button next to the Show dropdown.
The generated suggestions can be filtered out per selected AI agent, or all suggestions are displayed together.
Apply the suggested change directly - by clicking the Apply button, while reviewing the details of a content suggestion.
The textual change is persisted/stored in the system when the content editor saves or publishes the updated content item.
Discard the suggested change - by clicking the Dismiss button, while reviewing the details of a content suggestion.
Preview the suggested change applied inline in the content editor - by clicking Preview in editor.
Content editors need to confirm if they want to apply or discard the previewed change.
Restart the execution of the AI agent - by clicking (Refresh AI suggestions).
This action may result in receiving different content suggestions as the AI agents can adapt and learn from the rejected suggestions.

AI agents workflow orchestration and conflict handling

When you have custom AI agents configured in your Sitefinity backend, multiple AI agents (including the built-in AI agents) can be activated to analyze the same content item. These invoked AI agents interact with each other while performing their tasks in parallel.
In this scenario, AI agents workflow orchestration is introduced to coordinate the execution order of your multiple agents, manage conflicts between them, and prevent repetitive loops of AI-generated suggestions.

The AI agents orchestration logic in Sitefinity Cloud is based on Microsoft Agentic framework. Note that Administrators cannot configure a different Large Language Model (LLM) to be used.

When AI content suggestions from different active agents overlap, they are aggregated into a single suggestion before being surfaced. Each merged content suggestion on the UI indicates which AI agents contributed to it.

The AI agents track which content suggestions were applied or dismissed by content editors (the content suggestions are persisted as accepted and rejected). This way, with each run they adapt and avoid regenerating the same suggestions that the content editor has already acted on.

AI agents execution order

When multiple AI agents analyze the same content item, they are executed in parallel according to the following priority order:

First in order are the custom AI agents
Next in order is the built-in Search engine optimization Agent
Last in order is the built-in Brand voice and style Agent

Built-in AI agents take priority over custom agents and their suggestions override those from the custom agents when conflicts occur. The final unified content suggestions are then merged and surfaced on the UI.

Additional resources

Sitefinity AI overview