>>> [!note] Migrated issue <!-- Drupal.org comment --> <!-- Migrated from issue #3541329. --> Reported by: [yautja_cetanu](https://www.drupal.org/user/626050) >>> <h3 id="summary-problem-motivation">Problem/Motivation</h3> <p>Because AI is non-deterministic, a single succesful result does not necessarily mean the Agents are reliable. It would be good to get aggregate scores for the tests and make it easy to run multiple times.</p> <h3 id="summary-proposed-resolution">Proposed resolution</h3> <ul> <li>- When you run a test group, there is a form that allows you to pick the model. Default to 1 but have, No. of times to run this test group. These will then have to be run one after the other and so when a test group run ends it will have to re-direct to the next re-run of those tests automatically.</li> <li>- We should have an ability to run those tests concurrently if we are using an External client for the tests.</li> <li>- The Test Results page should have a summary that shows you the average success rate of the overall test groups and the average time. Each individual test should also have a summary of the average success rate and time.</li> </ul> <h3 id="summary-remaining-tasks">Remaining tasks</h3> <h3 id="summary-ui-changes">User interface changes</h3> <h3 id="summary-api-changes">API changes</h3> <h3 id="summary-data-model-changes">Data model changes</h3>