Monitor AI Agent Activity

TL;DR

Monitor deployed AI agents in the Agent Activity Dashboard to track actions, triggers, success/failure status, and AI reasoning. Use filters to debug runs and review logs weekly. To limit excessive actions, narrow agent scope with action filters, target specific item types, use triggered sub-items, and avoid placing agents on huge folders.

• Overview
• Agent Overview Table
• Filter AI Agent Activity Logs
• Viewing Detailed Action Logs
• Monitoring Best Practices
• How to Limit the AI Agent from Taking Too Many Actions
• What’s Next?

Overview

Once your AI agents are deployed, you can monitor their performance in the Agent Activity Dashboard within the AI agents management interface.

AI Agent Overview Table

• Status - shows whether the agent is currently active or inactive.
• Name - the name of the AI agent.
• Active locations – the locations where the AI agent is currently enabled. You can remove an agent from a location by clicking into the cell and selecting the × icon next to the location name. However, locations cannot be added manually and appear here only after the agent has been @mentioned in a comment in the location.
• Actions, this month – shows how many actions the agent has performed during the current month.
• Created by – the user who created the AI agent.
• Created on – the date the agent was created.
• Last updated by – the user who last updated the AI agent.
• Last updated on – the date of the agent was last updated.

Group by runs: When a single trigger fires an agent that takes several actions, you can group those actions together as one run, so the log shows one entry per execution instead of one row per action. This makes it easier to see what the agent did in response to a single event.

Filter AI Agent Activity Logs

Use the filter controls above the activity table to narrow the log and locate specific runs faster.

Filters available: Timestamp, Action, Work item, Triggered by, Status.

Useful in high-volume spaces where the agent has run hundreds of times - debug a failure by filtering to the failing status, or trace a specific work item's history.

Viewing Detailed Action Logs

1. Hover over the AI agent in the Agent Overview table.
2. Click the three-dot menu.
3. Select Show logs.

• Timestamp – when the action occurred.
• Action – the action performed by the agent.
• Work item – the item where the agent took action.
• Triggered by – the event that activated the agent.
• Status – whether the action succeeded or failed.

• The full path to the work item and its permalink 1.
• The precise action taken (for example, "Updated Request Category field to creative asset") 2.
• The AI agent's reasoning, explaining why the decision was made 3.

Monitoring Best Practices

• Regular review: Check AI agent activity logs weekly to make sure agents are working as expected.
• Reasoning analysis: Use the detailed reasoning display to understand decisions and spot opportunities to improve prompts.
• Success rate tracking: Monitor success and failure statuses to catch ongoing issues.
• Performance adjustment: Refine agent prompts based on activity logs to boost accuracy and consistency.

How to Limit the AI Agent from Taking Too Many Actions

Mind Your Scope - the most critical step in building effective automation.

• Avoid Select All: Selecting all available scopes can lead to unintended actions and performance issues.
• Use Action Filters to define exactly where an agent should operate.
• Target Specific Items: Configure agents to only work on specific item types or statuses (e.g., "active").

Leverage Triggered Sub-items

• Automate Project Blueprints: Set the agent to perform actions on all sub-items the moment the parent project's status changes.
• Action Precision: Ensures automation flows downward through a project structure exactly when needed.

Manage Folder Capacity

• Limit Item Counts: Do not place agents on folders with a massive number of items (e.g., 20,000 items).
• Prevent Performance Trouble: Large folder volumes can cause technical issues for the agent's processing.

What’s Next?

• AI Agent Limitations and Troubleshooting
• Write Effective Agent Prompts