Specialized agent logs

View and download execution logs for your specialized agents in Optimizely Opal. Logs record each execution's inputs, outputs, steps, timing, and credit usage. Use them to debug your agent, monitor performance, and evaluate output quality.

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 specialized agent logs

Follow these steps to view the logs:

1. Follow the steps in the Access your agents section.
2. Click the agent for which you want to view its logs or click More (...) > Edit Agent.

3. Select the Logs tab.

   

4. Click an execution to view its logs.

Specialized agent logs overview

Started

The specialized agent logs for executions still running display information like the following:

1. Status – Displays Started as the agent is running.
2. Stop Execution – Click to stop the agent.
3. Close – Close the execution details.
4. Version information – The version number and timestamp of when the agent was started.
5. Agent Name – The name of the agent invoked. Click Copy to copy the name to your clipboard.
6. Execution ID – The unique ID of the agent's execution. Use this ID to identify a specific agent run. Click Copy to copy the ID to your clipboard. See the Access a specialized agent's execution ID section for information.
7. Execution Time – The timestamp of when the agent was started.
8. Triggered By – The name of the user who started the agent.
9. Input Variables – The variables that were used in the execution. Click Copy to copy the variables to your clipboard to reference and debug agent runs.
10. Output – The agent response from Opal including any error messages. The output updates as the agent runs.

Completed and failed

The specialized agent logs display the following information for Completed and Failed executions:

1. Status – If the agent is Completed or Failed.
2. Version information – The version number and timestamp of when the agent was started.
3. Open in Test Run – Click to open the execution as a Test a specialized agent with the same variables from the execution already entered.
4. Close – Close the execution details.
5. Agent Name – The name of the agent invoked. Click Copy to copy the name to your clipboard.
6. Execution ID – The unique ID of the agent's execution. Use this ID to identify a specific agent run. Click Copy to copy the ID to your clipboard. See the Access a specialized agent's execution ID section for information.
7. Execution Time – The timestamp of when the agent was started.
8. Triggered By – The name of the user who started the agent.
9. Duration – The total time the agent took to run.
10. (Optional) Evaluation Score – The quality score for the execution, along with a Pass or Fail indicator. This field only displays if you added preferred output examples for the agent. It displays in two locations in the panel, see step 17.
11. Credits – Approximate credit usage for this execution. Final usage may vary slightly. See Optimizely Opal credits.
12. Input Variables – The variables that were used in the execution. Click Copy to copy the variables to your clipboard to reference and debug agent runs.
13. (Optional) Artifacts – A link to the canvas output if one was created during the execution's run. 
14. Output – The agent response from Opal including any error messages.
15. Rerun – Click to rerun the agent with the same variables as the execution.
16. Execution Memory – The steps Opal took during the execution. For multi-turn agents, Opal organizes memory by turn, with each turn displaying the user input and agent response. For single-shot agents, memory shows the steps Opal took to form its response, including tool calls and intermediate outputs.
17. (Optional) Evaluation Score – The quality score for the execution, along with a Pass or Fail indicator. This field only displays if you added preferred output examples for the agent. It displays in two locations in the panel, see step 10.

Export specialized agent execution logs

Download a record of your specialized agent's execution history as a comma-separated values (CSV) or Excel file. Use it to track usage, review inputs and outputs, and measure return on investment (ROI).

1. Follow the steps in the Access your agents section.
2. Click the agent for which you want to view its logs or click More (...) > Edit Agent.

3. Click More (...) > Export logs.

   

4. Select the columns you want to include. See Available columns. To clear all selections, click Deselect all.

5. Select your format, CSV or Excel, from the Format drop-down list. See Export formats.

   

6. Click Export.

Available columns

The following column groups are available for export:

• Execution Info – Agent Name, Execution ID, Execution Time, Triggered By, and Version.
• Input & Output 
  • Variables – Each input parameter gets its own column.
  • Output – The agent's response, one entry per execution.
• Performance – Status, Duration (seconds), and Evaluation Score (%).

Export formats

Choose from the following export formats:

• CSV – Plain text file that opens in any spreadsheet tool. Best for importing into other systems or doing programmatic analysis.
• Excel – Formatted workbook with bold headers and a text-wrapped output column. Best for handling long outputs gracefully.

Export limits and file details

Note the following constraints and naming conventions for exported files:

• Exports include up to 250 of the most recent executions. If your agent has more, the page displays the total count it exports.
• The file name matches your agent's name. For example, My_Agent-executions.csv.
• The Output column displays the error message for failed executions.
• The Triggered By column displays the full name of the user who ran the agent.

Set a specialized agent execution as an Output Eval

Set a specific specialized agent execution as a preferred output for Opal to evaluate its responses against. Opal uses the preferred output to create an Evaluation Score. Add up to five preferred outputs. Include at least three diverse outputs for the best results.

Follow these steps to set an execution as an output eval:

1. Follow the steps in the Access your agents section.
2. Click your specialized agent or click More (...) > Edit Agent.
3. Select the Logs tab.

4. Click More (...) for an execution and select Link as Output Eval.

   

Linking as an output eval automatically adds the execution to the specialized agent's preferred outputs. After configuring your preferred outputs, ensure you set the baseline quality score. See Add Output Evals for steps and information on what different scores mean. 

Access a specialized agent's execution ID

The Execution ID is a unique identifier for a specific agent run. Use it to reference a run in Optimizely Support requests, share it with collaborators, or monitor a long-running execution. Use the Execution ID for any of the following:

• Tracking and monitoring – Track the progress and status of a long-running agent execution.
• Retrieving results – Use the Execution ID to retrieve results when an asynchronous execution finishes.
• Debugging and auditing – Trace a specific run and review what happened. This is especially useful when diagnosing issues or unexpected outcomes.
• Sharing and support – Reference a specific agent run when working with support teams or collaborators.

Follow these steps to access an agent's Execution ID:

1. Follow the steps in the View specialized agent logs section.
2. Click the run whose execution ID you want to retrieve.

3. Click Copy for the Execution ID.