Monitor AI Agents

On This Page

The capabilities described on this page are included in Appian's advanced and premium capability tiers. Usage limits may apply.

Monitoring helps you understand how AI agents are being used, identify performance issues, and spot AI agents that may need instruction or tool refinements. The Monitor tab displays input and output variable values for each run alongside the existing Request column (which shows the agent's goal and instructions), so you can differentiate between runs of the same AI agent without opening individual run details.

For testing guidance, see Create and Configure an AI Agent.

Use the Monitor tab

The Monitor tab tracks how your AI agents are performing over time. The run history uses a timeline layout that displays each step chronologically—including tool calls, AI agent reasoning, and outputs—so you can follow the AI agent's execution path from start to finish.

Note: You can stop active AI agent runs clicking the Stop button. This is useful for canceling AI agents that are consuming excessive resources or producing incorrect results.

You can monitor your AI agents from two places:

The Monitor tab in the main navigation panel. This screen displays a log of all AI agent requests, including their current status and detailed metadata. Use this view to track the progress of each request, identify issues, and review historical activity. From this screen, you can click a Request ID to view detailed information about the AI agent's processing steps and outputs.

Scroll or drag to pan · ⌘+/⌘− to zoom · Esc to close
The AI agent-specific Monitor tab. To view request activity for a specific AI agent, open the AI agent and go to its Monitor tab. This shows only the requests handled by that AI agent.

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

You can also view all AI agent runs across all AI agents in the AI Agent Activity tab of the Monitor view.

Monitor chat agents

Chat agents appear in the agent-specific Monitor tab. When a chat agent is deployed via the agent chat component, end-user interactions generate runs that are visible in the chat agent's Monitor tab.

You can also view all AI agent runs across all AI agents in the AI Agent Activity tab of the Monitor view.

AI agent summary table

Each row in the table shows key metrics for an AI agent:

Field	Description
Run ID	A unique identifier for each request. Click to view the full request details.
Version	The version number of the AI agent that processed the request.
Status	The current state of the request.
Agent Name	The name of the AI agent that handled the request.
Request	A description of the request.
Input	The input variable values passed to the AI agent for the run, displayed as key-value pairs. Each variable appears on its own line in the format `Label: value`. Long values are truncated with an inline "show more" link to expand the full content. Document and file references render as clickable links. If an input variable has no value, the cell displays placeholder text.
Output	The output variable values produced by the AI agent run, displayed as key-value pairs. Complex data types (CDTs, records, maps) expand into a typed tree view. Document and file references render as clickable links.
AI Actions	The calculated consumption metric for the run. AI Actions represent the sum of all AI actions consumed across all tool calls within the run. This column is sortable, which helps administrators quickly identify AI agents consuming the most resources.
Tool Calls	The number of tools the AI agent used while processing the request.
Initiator	The person who initiated the request.
Duration	The time the AI agent took to complete the request.
Start Time	The date and time when the AI agent request began processing.

Input and output value display behavior

The Input and Output columns display variable values as key-value pairs, with one variable per line in the format Label: value. The display behavior applies consistently whether the run was triggered from Agent Studio or the Execute AI Agent smart service.

The following display rules apply to values in the Input and Output columns:

Document and file references: Document and file values render as clickable hyperlinks that open the referenced file.
Complex data types: CDTs, records, maps, and lists display a condensed summary by default. Click show more to expand into a typed tree view that follows the process variable display pattern, with indented key-value pairs and type annotations.
Empty values: If an input variable has no value (null or not provided), the cell displays placeholder text.

Search the run history grid

The search bar on the Monitor tab performs server-side search across all pages of the run history grid. Search returns results with accurate total counts, so you can locate specific AI agent runs without manually scanning the grid.

Server-side search matches against the following fields:

AI agent name
AI agent guidance (instructions)
Input variable values

Note: Output variable search is not available. Only input variable values are indexed for search.

How input values are indexed for search

Input variable values are indexed at run creation time. The system stores user-friendly text representations of input values—document names rather than IDs, space-separated words rather than camelCase—to maximize searchability. Full-word search is most reliable when searching for input values.

Runs created before Appian 26.10 do not have input variable values indexed for search. Only runs created after upgrading to Appian 26.10 are searchable by input variable content.

AI Actions in the run detail view

When you click a Run ID to open the run detail view, the Run Summary pane in the two-pane layout displays the total AI Actions consumed for that run. The Run Summary pane gives developers immediate feedback on the cost of a single execution without navigating away from the run details.

Stopped runs in the Monitor tab

When a user or developer stops a chat agent response using the stop button, the run appears in the Monitor tab with the status "Cancelled by User." The "Cancelled by User" status indicates that someone explicitly stopped the agent response rather than the system stopping it due to resource limits ("System Canceled").

Stopped runs behave as follows in the Monitor tab:

Status column: Displays "Cancelled by User."
Run preservation: The stopped run is preserved in the run history. It is not deleted.
Conversation continuity: Stopping does not end the conversation. The user can send a new message after stopping, which creates a new run in the same session.
Tool call count: The Tool Calls column reflects only the tool calls that completed or were in progress at the time the user clicked stop.

Tip: If you see frequent "Cancelled by User" runs for a specific chat agent, review the agent's instructions and tool configuration. Frequent terminations may indicate the agent is taking too long or going off-track, suggesting the need for more focused instructions or fewer tools.

MCP tool calls in the Monitor tab

When an AI agent calls an MCP tool, the tool call appears in the step history alongside native tool calls. Each MCP tool call shows the tool name, the request sent to the MCP server, and the response received.

MCP tool calls are counted in the Tool Calls metric for each run. They contribute to the same maximum tool call limit as native tools.

If an MCP tool call fails, the error message from the MCP server appears in the step details. Common failure reasons include authentication errors, server unavailability, and vendor-imposed rate limits.

Developer feedback in the Monitor tab

Developers with Viewer permissions or higher can provide feedback on their own AI agent runs directly from the Monitor tab. Click a Run ID to open the run detail view, then use the thumbs-up or thumbs-down control to rate the overall run outcome. To rate a single tool call instead, use the feedback control on that tool's card, including a tool that ran as part of a parallel batch.

Feedback submitted from the Monitor tab follows the same model as feedback in the Evaluate tab. Ratings contribute to evaluation metrics when the run is associated with a test case. For the full feedback workflow and evaluation metrics, see Evaluate AI Agents.

Parallel tool call display in run details

When an AI agent executes parallel tool calls, the run detail view groups those calls under a single step:

Step grouping: All parallel tool calls share the same step ID. The run detail view displays them as a grouped set to indicate concurrent execution.
Duration reporting: The duration for a parallel step reflects the wall-clock time from dispatch to completion of the last tool call, not the sum of individual call durations.

Progressive results—where each tool call card populates the moment its tool finishes—apply to the live test panel only. The Monitor tab shows tool results after the full batch completes. For the live test panel display, see Parallel tool call display in the run stream. For parallel execution constraints, see Parallel tool execution.

Feedback

Was this page helpful?