Specialized agent logs

  • Updated

You can view and download a log of a specialized agent's execution in Optimizely Opal. This helps you debug the agent and see how your agent is performing. 

Access your agents

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

  3. Select Opal.

    Click Opal

  4. Click Agents. 

  5. Select the Your Agents tab.

View specialized agent logs

To access the Logs of a specialized agent, complete the following steps:

  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

The specialized agent logs display the following information:

Specialized agent logs
  1. Status – If the agent successfully completed or failed.
  2. Version information – The version number and timestamp of the version of the agent that was ran.
  3. Open in Test Run – The way to open the execution as a test run with the variables entered filled in. See Test a specialized agent.
  4. Close – The way to close the execution and return to the specialized agent's logs. 
  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 more.
  7. Execution Time – The timestamp of when the agent executed in UTC.
  8. Duration – The total time of how long the agent took to execute.
  9. (Optional) Quality Score – The quality score for this execution, along with a Pass or Fail icon, if you configured the preferred output for the agent.
  10. 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.
  11. Output – The response from Opal including any error messages.
  12. Execution Memory – The memory chunks the agent transversed during the agent's execution.
  13. (Optional) Quality Score – The quality score for the execution, the Baseline Quality score for the agent, and the Evaluation Feedback, if you configured the preferred output for the agent.

Export a specialized agent execution logs

Download a record of your specialized agent's execution history as a CSV or Excel file to track usage, review inputs and outputs, and measure 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.
    • Click Deselect all to clear all selections.

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

  6. Click Export.

Available columns

  • 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

  • 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 very long outputs gracefully.

Things to know

  • 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

You can set a specific specialized agent execution as a preferred output that Opal can use to evaluate its responses against. The preferred output is used to create an Evaluation Score. You can add up to five preferred outputs and you should add at least three diverse outputs. See Add Output Evals for more information.

To set an execution as an Output Eval, complete the following:

  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.

This 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 run of an agent. You might need it for the following reasons:

  • Tracking and monitoring – It lets you track the progress and status of a long-running agent execution.
  • Retrieving results – If an agent's execution is asynchronous or takes time, you can use the Execution ID to retrieve the results once the agent has finished its work.
  • Debugging and auditing – In case of issues or unexpected outcomes, the Execution ID helps in tracing back the specific run, reviewing logs, and understanding what happened during that execution.
  • Referencing – It provides a concrete reference point when discussing a particular agent run with support teams or collaborators.

To access an agent's Execution ID, complete the following:

  1. Follow the steps in the View the agent logs section.
  2. Click the agent's run you want to retrieve its execution ID.

  3. Click Copy on the Execution ID.