Agentforce Testing Center
Build confidence in your AI agents and deliver seamless, effective interactions with thorough testing. Easily generate custom test scenarios and leverage our expert evaluation tools to assess response accuracy, conversation quality, subagent recognition, action execution, and knowledge retrieval. Identify issues early and fine-tune your agent’s behavior with precision.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
- Running tests consumes requests and credits. See Considerations for Testing Center.
- Testing agents can modify CRM data. To avoid issues, be sure to use Testing Center only in your sandbox environment.
With Testing Center, you can quickly generate test cases from your agent’s core subagents and actions, create Q&A style tests from your knowledge content, or upload custom scenarios tailored to your specific needs. Because AI agents are non-deterministic, it's essential to test them across a wide range of scenarios to ensure consistent and accurate performance.
Testing Center supports large-scale batch testing through a range of evaluations. These include response accuracy, subagent and action validation, and key quality metrics such as completeness, coherence, conciseness, latency, and instruction adherence. By surfacing patterns and edge cases often missed in smaller-scale testing, you’ll get a fuller picture of your agent’s performance. With these insights, you can close performance gaps, refine subagent instructions, and continuously improve your AI agent’s responses.
- Set Up and Run Tests in Agentforce Studio (Beta)
Experience a more flexible, AI-driven testing workflow with Testing Center in Agentforce Studio (beta). Build test cases, manage test suites, and track test history, all in a spreadsheet-inspired interface that makes it easier to validate and debug agent conversations. Fast-track testing with AI-generated scenarios for specific subagents and actions, or data linked through an Agentforce Data Library, or manually craft and upload your own. Then select evaluations to run on your test cases or develop your own custom evaluations for your business needs. - Set Up and Run Tests in Setup (Legacy)
Efficiently validate your agent’s performance at scale, whether you want to fast-track testing with AI-generated scenarios or manually craft and upload your own. You can generate realistic test cases for specific subagents and actions, or data linked through the Agentforce Data Library. - Use the Test Results
Once your tests finish running, you’ll see overall metrics for the test suite along with evaluation scores for each test. Use these results to identify failed or low-scoring utterances, then manually retest them in Agentforce Builder. Refine the instructions within your subagents and actions, and iterate until you’re satisfied with the responses. Pay close attention to recurring failures as these results can help uncover underlying issues such as unclear guidance, missing knowledge, or configuration issues. To interpret your results, see how each evaluation helps to measure agent performance. - Considerations for Testing Center
To use Testing Center, consider supported functionality, usage, limitations and allowances, limits, and other issues.
