Skip to main content

​
Losses

A cell is a loss when a competing tool or Built its own is a top pick and your tool was not installed in a majority of completed runs. A joint top pick counts. For example, seven installs out of eight is not a loss. Four installs out of eight with a competing tool tied at four is a loss because your tool has no majority. A tool absent from the test is unmeasured and does not create a zero-install loss.

​
Actions

Open Actions to find Agent Picks Actions in the shared queue. Use the Source filter (AI Search only, Agent Picks only or Both) to choose the work shown. Both includes the sources you can access. AI Search tracking requires its own plan. Completed tests create two kinds of Action:
  • A loss Action for a losing environment, request, agent and model combination.
  • A reason Action when the same recorded reason appears across several losing cells, such as a failed page fetch. It lists every affected cell and its evidence.
Open the Action to review the original install count, completed and planned runs, likely range and recorded evidence. A failed fetch is an observation, not proof it caused the loss. Copied public tests can supply baseline rates while their original run evidence is unavailable; the Action says when evidence is missing.

​
Draft

Use the Action’s brief and draft controls to prepare a fix. Review the proposed content and approve it before publishing. If a page is locked, the suggestion names it and calls for supplementary content around it. You can dismiss an Action and restore it later. If a newer Action already tracks the loss, restoring the older one is refused and the newer Action stays in the queue.

​
Shipping and re-testing

  1. Publish the fix and select Mark live on the Action.
  2. Open the live Action and select Estimate a re-test under Re-test this fix.
  3. Review the estimate, then select Confirm and reserve credits.
A complete original measurement is required. If a recorded page on your domain returned 404, that page must load before the re-test can start. If the original test environment is no longer supported, run a fresh project test first. The re-test uses the Action’s original requests, environments, agents and models. Changing your saved setup does not widen it. Only one paid test, including a re-test, can run in the project at a time. Re-tests run in batches of eight, up to 40 runs total. They stop early when the before-and-after likely ranges separate. For a reason Action, runs rotate across its recorded cells and stop early only when every cell’s ranges separate. Unstarted runs stopped at that point are reported separately from failures, and unused credits return through the normal settlement.

​
Results

Use the Source filter in Results to find Agent Picks results. Each comparison keeps its before-and-after counts, likely ranges and coverage. Shipping alone does not establish improvement. A later re-test sets the current result back to Still measuring until it finishes. These are observed install results, not citation or traffic results, and they do not prove causation.