Workflow agent logs

After your workflow agent runs, you can view a log of that execution in Optimizely Opal to debug the agent and see how it is performing.

Use the Agent activity logs tab to see execution activity across all agent types.

Access your agents

1. Go to home.optimizely.com.
2. Select your organization.

3. Click Opal.

   

4. Click Agents.

   

5. Click the Your Agents tab.

   

View the logs

Workflow agent logs are accessible from two locations, the Agents page and the workflow editor.

From the Agents page

To access the logs of a workflow agent from the Agents page, complete the following:

1. Complete the steps in the Access your agents section.

2. Select the Workflow Logs tab.

   

3. Click a workflow's execution to view its logs.

From the workflow editor

1. Complete the steps in the Access your agents section.
2. Click the agent name, or click More (...) > Edit Agent.
3. Click More (...) > View Logs.
4. Click an execution to view its logs.

Execution statuses

The Status column on the Workflow Logs tab displays the current state of each workflow agent execution. The column displays one of the following statuses:

• Pending – Queued but not yet started.
• Running – Currently executing.
• Completed – Finished without errors.
• Failed – Stopped because of an error.
• Stopped – Opal halted the execution.
• Canceled – A user canceled the execution.

Workflow agent log overview

Started

The workflow agent's log that is still running displays similar to the following:

1. Details – Toggle the details panel on or off.
2. Name – The name of the workflow agent.
3. Status – Indicates the workflow agent is still running.
4. Timestamp – The timestamp of when the workflow agent started.
5. Status – Indicates the workflow agent is still running.
6. Cancel Execution – Stop the workflow agent.
7. Close details – Close the details panel of the execution.
8. Agent Name – The name of the workflow agent.
9. Execution ID – The unique ID of the workflow agent's execution. Use this ID to identify a specific agent run.
10. Execution Time  – The timestamp of when the workflow agent executed started.
11. Triggered By – The name of the person who ran the workflow agent. If the workflow agent is started from a webhook, the user who created the workflow agent displays instead.
12. Input Variables – The variables that were used in this execution. Click Copy to copy the variables to your clipboard to easily reference and debug agent runs.
13. Output – Opal's response including any error messages.
14. Execution Memory – The memory chunks the agent transversed during the agent workflow's execution. 
15. Trigger – The trigger that started the workflow agent.
16. Agents run in this workflow – The overview of the agents invoked in this execution. They display as gray because they have not run yet.
17. Close – Return to the list of the workflow agent's executions. 
18. Overview map – A smaller, "picture-in-picture" view of the entire workflow agent.

Completed and failed

The workflow agent's log with a Completed or Failed status displays similar to the following:

1. Details – Toggle the details panel of the execution on or off.
2. Name – The name of the workflow agent.
3. Status – Whether the workflow agent completed or failed.
4. Timestamp – The timestamp of when the workflow agent started.
5. Status – Whether the workflow agent completed or failed.
6. Close details – Close the details panel of the execution.
7. Agent Name – The name of the workflow agent.
8. Execution ID – The unique ID of the workflow agent's execution. Use this ID to identify a specific agent run.
9. Execution Time  – The timestamp of when the workflow agent started.
10. Triggered By – The name of the person who ran the workflow agent. If the workflow agent is started from a webhook, the user who created the workflow agent displays instead.
11. Duration – Total time of how long the workflow agent took to execute.
12. Credits – Approximate credit usage for this workflow. This total accounts for both the workflow orchestrator and specialized agents used. Final usage may vary slightly. See Optimizely Opal credits.
13. Input Variables – The variables that were used in this execution. Click Copy to copy the variables to your clipboard to easily reference and debug agent runs.
14. Output – Opal's response including any error messages.
15. Execution Memory – The memory chunks the agent traversed during the agent workflow's execution. 
16. Trigger – The trigger that started the workflow agent.
17. Agents run in this workflow – The overview of the agents invoked in this execution. Click on agents to see their Execution and Agent Details. Click View Agent to view or modify the agent's details. See Specialized agent logs overview for information.
18. Close – Return to the list of the workflow agent's executions. 
19. Overview map – A smaller, "picture-in-picture" view of the entire workflow agent.

Additional elements

Logic elements

If your workflow agent includes logic elements, such as a Condition or Loop, Opal tracks the following execution statuses in the logs:

• Pending – Not yet started.
• Running – Currently executing.
• Completed – Finished successfully.
• Failed – Encountered an error.
• Skipped – Intentionally skipped.
• Canceled – Canceled by user.

Tools

If agents in the workflow include tool calls, the parameter generation logs display within the Thinking chunks of the workflow execution log. The logs capture how Opal interprets input, isolates the required parameters, and formulates the JSON structure passed from one agent to the next. Use this information to verify that parameters were predicted as expected or to diagnose issues when a workflow produces unexpected results.

For example in the following image, Opal distills a user's starting input into a structured parameters object, such as a news_topics field populated with relevant values. 

Ask Opal about an execution

Use Opal Chat to ask questions about a workflow agent execution in natural language. Chat helps you understand what happened during a run without reading through every step and memory chunk manually.

Start a chat-based debugging session using one of the following methods:

• Open Opal Chat from the execution log details view to load the execution context automatically.
• Open Opal Chat directly and reference the execution ID in your prompt (for example, Debug execution abc-123).

After Opal loads the context, ask questions such as the following:

• Why did the agent fail at step 3?
• Which workflow step took the longest?
• What were the inputs to the step that failed?
• What was the total token usage?
• Show me the full tool call sequence.

Opal restricts execution debugging to your instance.