Whatever message this page gives is out now! Go check it out!

Monitor AI services in ColdFusion Performance Monitoring Toolset

Last update:
May 18, 2026
Set up and use AI Services monitoring to track agents, LLMs, vector stores, RAG pipelines, and MCP connections in your ColdFusion application.
For an overview of what each tab shows, see AI Services monitoring overview.

Enable PMT for AI Services

IMPORTANT: As a prerequisite, you must enable AI Services monitoring in Settings. See Configure Performamce Monitoring Toolset settings for more information.
  1. Open the Performance Monitoring Toolset.
  2. Select AI Services on the left pane.
  3. Use the AI Services tabs to pick what you want to monitor. This guide focuses on Agents; other tabs (such as LLMs, Vector Stores, RAG, MCP Clients, MCP Servers) show related metrics.

Launch AI Services monitoring

  1. Open the Performance Monitoring Toolset.
  2. Select AI Services on the left pane.
  3. Select a tab to view the metrics you need: Agents, LLMs, Vector Stores, RAG, MCP Clients, or MCP Servers.

Configure the time range

Use the time-range picker at the top of the page to scope the data window.
  1. Select a preset button: 1M (1 minute), 1H (1 hour), 1D (1 day), 1W (1 week), or 1Mo (1 month).
  2. For a custom range, select the calendar icon next to 1Mo and choose a duration such as "Last N minutes" or "Last N days." The selected range applies to all time-series charts and most summary tables on the current tab.

Filter by AI service

Use the Select AI Services dropdown to narrow data to specific services.
  1. Open the Select AI Services (max 5) dropdown at the top of the page.
  2. Select up to five services. Your selection is saved in the browser and persists across sessions.
Note: The RAG tab does not honor the Select AI Services dropdown. It always aggregates across all RAG-enabled services. Only the time-range picker scopes data on the RAG tab.

View trace details for a request

  1. In any grid table that includes a Trace column, locate the row you want to investigate.
  2. Select View Trace in that row. The Trace Details modal overlay opens on top of the current page.
  3. Use the three tabs inside the modal:
    • Timeline — View the execution timeline. Hover or click a span bar for details.
    • Basic Info — View summary fields such as Operation, Duration, and Status.
    • All Spans — View a sortable table of every span in the trace.
Tip: The MCP Servers tab does not have trace links. To trace an MCP server operation, switch to the MCP Clients tab and locate the same operation there.

Troubleshooting

Charts show a flat line at 0 ms
A flat line typically means no traffic matched the current filters and time range. Widen the time range or confirm that your application is generating AI service calls in the selected environment.
"There is no data available" in a grid table
This message appears when no qualifying data exists for the current filters. Widen the time range, check that the correct services are selected, or verify that the feature is enabled.
"All entries have zero values" in a pie chart
This means no events of that type (such as errors) were recorded in the selected window. This is normal for healthy deployments with no errors.
Cannot add more than 5 services to the filter
The Select AI Services dropdown enforces a maximum of 5. Deselect a service before adding a new one.

Share this page

Was this page helpful?
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Thank you for your feedback. Your response will help improve this page.
Previous page AI Services monitoring in ColdFusion Performance Monitoring Toolset
Next page AI Services monitoring tab and widget reference

On this page