--- title: "Set Up A/B Testing" slug: "set-up-a-b-testing-for-guides" updated: 2026-07-20T04:44:21Z published: 2026-07-20T04:44:21Z canonical: "help.gladly.com/set-up-a-b-testing-for-guides" --- > ## Documentation Index > Fetch the complete documentation index at: https://help.gladly.com/llms.txt > Use this file to discover all available pages before exploring further. # Set Up A/B Testing | **REQUIRED USER ROLE** Administrator | **PERMISSION OVERVIEW** [View permissions by role](https://help.gladly.com/docs/managing-users-and-roles#roles-and-responsibilities) | | --- | --- | A/B testing allows you to split incoming Conversation traffic across two different Gladly Agent configurations. You can compare two different Gladly Agents or test two versions of the same agent to evaluate which setup performs better before committing to a change. A/B testing is configured per [Entry Point](/product-docs/docs/manage-entry-points), giving you control over which specific Channels and Entry Points are part of a test. You can run tests at any traffic split you choose, and end the test at any time. ![Entry points configuration showing traffic distribution and A/B testing options for agents.](https://cdn.us.document360.io/7047b671-c4f2-4df0-bb0a-b9b511fd2452/Images/Documentation/entry points ab test.png) ## Before you begin A/B testing is set up from the Entry Points page and requires at least one entry point already connected to a Gladly Agent. If you haven't done this yet, see [Connect or Disconnect Gladly Agents from an Entry Point](https://help.gladly.com/docs/connect-or-disconnect-gladly-ai-from-an-entry-point). ## Set up an A/B test 1. From the **AI Agents page**, click the Gladly Agent name dropdown at the top of the page, then select **Connect Entry Points**. ![Dropdown menu showing options for Retalè World and related features.](https://cdn.us.document360.io/7047b671-c4f2-4df0-bb0a-b9b511fd2452/Images/Documentation/connect entry (1)(1).png) 1. Alternatively, you can click **Entry Points** from the main navigation bar. ![Gladly AI interface showing various management options with 'Entry Points' highlighted.](https://cdn.us.document360.io/7047b671-c4f2-4df0-bb0a-b9b511fd2452/Images/Documentation/entry points call out.png) 2. Locate the **entry point** you want to test. 3. Click **+ Add A/B test** below the entry point row. ![Overview of A/B testing options for different websites with highlighted elements.](https://cdn.us.document360.io/7047b671-c4f2-4df0-bb0a-b9b511fd2452/Images/Documentation/add a b test.png) 4. Two rows appear — one for each leg of the test. For each row, configure the following: - **%:** the percentage of traffic routed to that leg. The two values must add up to 100. Adjusting one automatically updates the other. - **Agent:** select any live Gladly Agent. Both legs can use the same agent or different Gladly Agents. - **Version:** select a version of the chosen Gladly Agent. Choose **Always latest** to always use the most recently saved version, or select a specific saved version by timestamp. ![](https://cdn.us.document360.io/7047b671-c4f2-4df0-bb0a-b9b511fd2452/Images/Documentation/ab options(1).png) 5. Click **Save**. The entry point row updates to show **A/B test** in the Agent column and the configured traffic split in the Traffic column. ## Edit an active A/B test To adjust the Gladly Agents, versions, or traffic split for an active test: 1. Select **Entry Points** from the left sidebar under Deploy. 2. Locate the entry point with an active A/B test. 3. Update the **%**, **Agent**, or **Version** values directly on the variant rows. 4. Click **Save**. ## End an A/B test To stop an A/B test and return the entry point to a single Gladly Agent: 1. Select **Entry Points** from the left sidebar under Deploy. 2. Locate the entry point with an active A/B test. 3. Click the delete icon on the variant row you want to remove. 4. Click **Save**. The remaining variant becomes the sole configuration for that entry point. ## Review A/B test results Once an A/B test is running, results are available in two places: - [Gladly Improvement Opportunities dashboard](https://help.gladly.com/product-docs/docs/gladly-improvement-opportunities) - [Gladly AI Sessions report](https://help.gladly.com/product-docs/docs/set-up-a-b-testing-for-guides#gladly-ai-sessions-report) ### Gladly Improvement Opportunities dashboard [The Gladly Improvement Opportunities dashboard](/product-docs/docs/gladly-improvement-opportunities) includes two filters specifically for A/B testing: **Entry Point** and **Experiment Traffic Split**. Use the **Entry Point** filter to narrow the dashboard to a specific entry point where a test is running. Use the **Experiment Traffic Split** filter to select a specific test. Once filtered, the existing dashboard tiles update to reflect only the sessions from that experiment. Each Gladly Agent version in the test appears as a separate row across tiles, making it possible to compare resolution rates, handoff rates, response rates, and recontact rates side by side. The Gladly AI Agent Outcomes tile and the Handoff Opportunities Prioritization table are particularly useful for assessing which configuration is performing better. > [!NOTE] > Historical data is not available prior to creating a test > > Entry Point and Experiment Traffic Split data is only available for sessions created after the A/B testing feature was enabled. Historical session data will not include these fields. ### Gladly AI Sessions report The Gladly AI Sessions report, accessible via Reporting in Gladly Team, also includes **Entry Point** and **Traffic Split** as filterable fields. This report provides session-level data and can be exported as a CSV for more granular analysis outside of the dashboard.