Skip to main content
Running an AI agent in Superhawk AI kicks off an automated analysis of your trial data. You can run agents for a single trial or in batch across multiple trials.

​
How to Run an Agent

1

Navigate to a trial or the Agents page

You can start an agent run from two places: directly from a trial’s detail page by clicking Run Analysis, or from the dedicated Agents page in the sidebar.
2

Select the agent to run

Choose the agent you want to run. The Trial Analyst is the primary agent, analyzing session recordings, CRM data, and call transcripts together.
3

Choose the scope

Select whether to run the analysis on a single trial or in batch across multiple trials. Batch runs are useful when you want to refresh analysis across your entire pipeline.
4

Click Run

Click the Run button to start the analysis. The agent begins processing in the background.
5

Monitor progress

Track the status of your agent run in the agent runs list. Each run shows its current status: Queued, Running, or Completed.
Agent runs can take a few minutes depending on the volume of data being analyzed. A trial with many session recordings and call transcripts will take longer than one with minimal data. You’ll receive a notification when the run is complete.

​
Notifications

When an agent finishes its run, Superhawk AI notifies you so you don’t have to keep checking. Notifications appear in the app, and if you have Slack connected, you can receive notifications there as well.

​
Re-Running Analysis

You can re-run an agent on the same trial at any time. This is useful when:
  • New session recordings or call transcripts have been added since the last run
  • CRM data has changed significantly
  • You want to track how engagement trends are evolving over time
Each run generates a new report, so previous results are preserved for comparison.
After an agent completes, head to the trial’s analysis section to review the results. See Trial Analysis Reports for details on what the report includes.