Select Scorers
Scorers measure your AI agent’s performance across key areas. Default scorers are always tested, but you can select quality metrics to focus your tests on specific areas.
Required Editions
 This article applies to: |
New Testing Center in Agentforce Studio (Beta) |
 This article doesn’t apply to: |
Legacy Agentforce Testing Center in Setup |
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
| User Permissions Needed | |
|---|---|
| To create tests in the Testing Center: | Manage Agentforce Grids AND Manage Agentforce Testing |
Default scorers include response accuracy, subagent assertion, and action assertion. To match your testing goals, you can add quality-focused scorers like completeness, coherence, conciseness, and latency. Selecting the right mix of scorers gives you the best insights to strategically refine and improve your agent.
Once Agentforce finishes generating tests, they appear under Test Cases. Depending on the size and complexity of the request, this process can take anywhere from a few minutes to several hours. You may need to refresh the testing suite to see your test cases.
From Testing Center, you can edit the tests inline or download them as a CSV.
- Default Scorers
Default scorers measure your AI agent’s performance across response accuracy, subagent assertion, and action assertion. - Run Quality Scorers
Response quality scorers measure your agent's accuracy and relevance. - Create Custom Scorers
Custom scorers help you test your AI against specific criteria like accuracy, tone, and brand voice. By using an LLM-as-judge, you can automatically score and review outputs to make sure that your agents' responses consistently meet your specific goals and quality standards.
