AI Agent Screen Reference

Appian Designer provides a streamlined screen for creating, managing, and optimizing your AI agents. Use this screen to configure AI agent behavior, test functionality, and monitor performance. This reference explains each interface element and its purpose.

For step-by-step configuration guidance, see Create and Configure an AI Agent. For foundational concepts, see About AI Agents.

Tabs

The screen includes these main tabs that organize your work.

• Build
• Monitor

Build

The Build tab provides a unified workspace for creating, configuring, and testing your AI agents. The interface uses a split-pane layout with the Configure panel on the left and the Test panel on the right, so you can see your AI agent's complete configuration alongside step-by-step test results.

Scroll or drag to pan · ⌘+/⌘− to zoom · Esc to close

The Instructions field supports Markdown formatting to help you structure and style your content. Use the Preview tab to switch between the raw Markdown editor and the rendered view.

By default, the field displays raw Markdown syntax to allow for immediate editing. Click Preview when you need to see how the rendered Markdown displays.

Scroll or drag to pan · ⌘+/⌘− to zoom · Esc to close

Configure panel (left): View, create, and manage your AI agent settings including instructions, inputs, outputs, and tools. Changes made in this panel are automatically saved when you run a test.

Test panel (right): Validate your AI agent's behavior by providing input values and observing how your AI agent responds. You can use simple form fields for basic data types or write SAIL expressions for complex types like records, CDTs, and maps. The Load Test Case dropdown allows you to quickly reuse saved test configurations. When you save a test case, your expressions are saved too, so you can reuse and modify them later.

When you configure an input as an array using the Array (multiple values) checkbox, you'll need to use constant or expression options to define your test lists. Static values aren't available for array inputs.

The side-by-side layout eliminates the need to switch between separate views, creating a more direct feedback loop for building and refining your AI agents. For step-by-step guidance, see Create and Configure an AI Agent and Monitor AI Agents.

Monitor

You can track how your AI agents are performing over time. This tab shows key metrics for each AI agent, including the AI agent run status, number of tool calls, successful completions, and average run duration. These insights help you measure efficiency, spot trends, and identify areas for improvement. The run detail view accessed from this tab also includes a Stop button for canceling active AI agent runs. For monitoring best practices, see Monitor AI Agents.

Scroll or drag to pan · ⌘+/⌘− to zoom · Esc to close

Inputs and outputs

Inputs and outputs define the data your AI agent receives and returns. You configure them directly in the Inputs and Outputs sections of the Configure panel on the Build tab. When configuring these variables, you can specify whether each variable accepts a single value or multiple values.

Array (multiple values)

When defining an input or output variable, you can select the Array (multiple values) checkbox to allow the variable to accept or return a list of values instead of a single value. Selecting this checkbox changes the variable signature from a single data type to a list of that data type.

For example:

• A Document input without the checkbox accepts one document.
• A Document input with the checkbox accepts a list of documents.

This capability allows you to pass multiple items directly to your AI agent or receive structured lists as outputs without building complex looping logic. List values are formatted for better readability throughout the AI agent screen.

Tools

Tools are design objects that enable AI agents to access or act on data, processes, and documents.

Tool	Description
Process	Starts a process model in Appian to perform a series of predefined tasks or workflows.
AI Agent	Collaborates with another AI agent to complete a task, providing a way to orchestrate a modular, multi-agent workflow.
Document	Provides the AI agent with context from a single document.
Document folder	Gives the AI agent access to multiple documents stored in a folder.
Record	Allows the AI agent to retrieve data from record types.
Rule	Uses expression rules or decisions to provide logic or data.

Feedback