The Managed Agent Activity Feed gives you a unified view of live conversations and automated runs so you can monitor activity, review execution details, troubleshoot agent behavior, and provide feedback on individual Managed Agent replies.

This guide explains how to use the Activity Feed, understand run data, review execution logs, debug agent activity, and rate individual replies.

TABLE OF CONTENTS

What Is the Managed Agent Activity Feed?

The Activity Feed is a timeline inside each supported Managed Agent that displays recent runs and activity in reverse chronological order, with the newest activity first.

It brings live conversations and automated trigger executions into one view. Automated runs can include form submissions, tag changes, Facebook lead form submissions, survey submissions, and other supported trigger events.

Facebook lead form runs can appear as Facebook Lead Form Submitted, while survey-triggered runs can appear as Survey Submitted. Each run includes status and timing information to help you confirm that the event started the Managed Agent.

Each Activity Feed row can include:

  • An icon representing the run type

  • Run status

  • Timestamp

  • Trigger type

  • Context describing what started the agent

Open a run to review its execution details, including completed steps, skills and tools used, inputs and outputs, and the final response.

Key Benefits

  • Full visibility: Review conversations and automated runs in one chronological view.

  • Faster debugging: Inspect execution steps, skills, and tool calls to identify issues more quickly.

  • Trust and transparency: Review what happened during an automated run using detailed execution information.

  • Simplified monitoring: Review conversation and automation activity without switching between separate views.

  • Performance tracking: Review timing and token-usage metrics to identify slow steps or high-usage runs.

  • Feedback-driven improvement: Rate individual Managed Agent replies so successful responses and misses stay connected to real conversation examples.

How to Use the Activity Feed

Use the Activity Feed to review recent Managed Agent runs, inspect execution details, and provide feedback on individual replies.

  1. From your Account, go to AI Agents → Agent Studio → Managed Agents and open the Managed Agent you want to review.


  2. Open the Activity tab. Recent runs appear in reverse chronological order.


  3. Review the run status, timestamp, trigger type, and available context in the Activity Feed.


  4. Select the applicable run or conversation to open its execution details.


  5. Review the Agent Conversation View and execution timeline to understand what occurred during the run.


The complete navigation path is:

Account → AI Agents → Agent Studio → Managed Agents → select the Managed Agent → Activity → open the applicable run or conversation


When reviewing a conversation, individual Managed Agent replies can also be rated using the available thumbs up and thumbs down controls.



Tip: During testing, use the Activity Feed to confirm that the Managed Agent's skills and triggers behave as expected. When troubleshooting, review the execution timeline to identify where an issue occurred.

Understanding Activity Feed Data

Each Activity Feed entry provides information about a specific Managed Agent run. These details help you identify how the run started and what happened during execution.


Run Icon

The icon identifies the type of activity. Automated trigger runs can use a lightning-bolt icon, while live conversations can use a chat icon.


Run Status

The status indicates whether the run completed successfully, failed, or is still in progress.


Timestamp

Each run displays when it started, helping you correlate agent activity with user actions, submissions, or automation events.


Trigger Type

The trigger label identifies whether the activity was initiated through a trigger or a conversation.


Context Description

For automated runs, the context can identify the form, tag event, survey, or other event that started the agent. For conversation runs, it can provide a preview of the user's message.

Use the event name, status, timestamp, and context together to trace activity back to its source before opening the complete run details.


Viewing Execution Logs


Opening a run from the Activity Feed displays its execution details. Use this view to review the Managed Agent's conversation, completed steps, tool usage, timing, and results.


Agent Conversation View

The Agent Conversation View displays the conversation and Managed Agent responses associated with the run. Use it to review the conversation context and individual responses.


Rate Managed Agent Replies

Individual Managed Agent replies can be rated directly from the Agent Conversation View.

  • Thumbs up: Use a positive rating when the reply was useful, accurate, and appropriate for the conversation.

  • Thumbs down: Use a negative rating when the reply included wrong information, missed important context, took an inappropriate action, or was otherwise off-base.


Selecting thumbs down opens a short follow-up where you can explain what went wrong. You can also add an optional note when additional context would help.

Feedback is attached to the specific Managed Agent reply that was rated, keeping the feedback connected to the exact conversation response being reviewed.

After a rating is submitted:

  • The selected rating remains visible when you return to the conversation.

  • Previously rated replies do not appear as unrated again.

  • You can reopen a previous rating to review the feedback that was submitted.

Positive ratings highlight replies that are working well, while negative ratings provide concrete examples of misses. These examples can help when reviewing prompts, instructions, knowledge coverage, or overall agent behavior.

Execution Timeline

The execution timeline shows the steps completed by the Managed Agent during the run in sequential order, including timing and token usage where available.

Use the timeline to review which skills or tools were used and identify where a run behaved differently than expected.


Execution Controls and Metadata

The execution view can also include the conversation title and available controls such as refresh, timing metrics, token usage, Copy ID, and View in Agent Logs.


Frequently Asked Questions


Q: Where can I find the Managed Agent Activity Feed?

Go to Account → AI Agents → Agent Studio → Managed Agents, open the Managed Agent, then select Activity.


Q: What types of runs appear in the Activity Feed?

The Activity Feed can include live conversations and supported automated runs such as form submissions, tag events, Facebook lead form submissions, survey submissions, and other Managed Agent trigger events.


Q: How do I debug a failed Managed Agent run?

Open the applicable run from the Activity Feed and review the Agent Conversation View and execution timeline to identify where the issue occurred.


Q: Can I review activity for multiple Managed Agents in one Activity Feed?

No. The Activity Feed is specific to each Managed Agent. Open the Activity tab for each agent you want to review.


Q: What do timing and token-usage metrics show?

Timing metrics show how long supported execution steps or the overall run took. Token-usage metrics show the number of tokens consumed where that information is available.

Need Help?

If a Managed Agent run does not behave as expected:

  • Confirm that you opened the correct Managed Agent and Activity entry.

  • Review the run status and trigger context.

  • Check the Agent Conversation View for the response associated with the issue.

  • Review the execution timeline for unexpected steps, skills, or tool behavior.

  • Check timing and token-usage information where available.

  • Use the run ID when additional troubleshooting or support is required.

If the issue continues, collect the affected Managed Agent name, run ID, relevant input and output, any visible error message, and screenshots of the execution details before contacting support.