Loading
Upcoming Mandatory Changes to Public Key Infrastructure (PKI)Read More
Salesforce Enforces New Security Requirements in Summer 2026Read More
Agentforce and Einstein Generative AI
Table of Contents
Filter by (0)Add
Select Filters

          No results
          No results
          Here are some search tips

          Check the spelling of your keywords.
          Use more general search terms.
          Select fewer filters to broaden your search.

            Search all of Salesforce Help
            Search all of Salesforce Help
            Set Up and Run Tests in Setup (Legacy)

            You are here:

            1. Salesforce Help
            2. Docs
            3. Quickstart Your Einstein Generative AI Solution

            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.

            Required Editions

            green checkmark

            This article applies to:

            		 Legacy Agentforce Testing Center in Setup
            red crossmark

            This article doesn’t apply to:

            		 New Testing Center in Agentforce Studio (Beta)
            Available in: Lightning Experience
            Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.

            Start by selecting the agent you want to test and configuring key conditions like conversation history and context variables to match your real-world use case. Then, choose your test data: generate scenarios to validate the agent’s selection of subagents and actions, generate question-and-answer style test cases based on the knowledge content available to the agent, or upload your own test cases in a CSV file for full control. Then, select the evaluations that best measure your agent’s performance ranging from basic response accuracy to deeper quality metrics like coherence, completeness, and instruction adherence. You can run tests immediately or download the cases for review and refinement before execution.

            1. Create a Test
              Fast-track your testing with AI generated testing scenarios or create and upload your own. Test your agents against ‌subagents and actions or data available in Agentforce Data Library.
            2. Define Test Conditions
              When you upload test cases from the CSV template, defining test conditions such as conversation history and context variables helps provide additional context. These variables help simulate more realistic user interactions, making your tests more reliable and reflective of actual agent behavior.
            3. Add Test Data
              Add test cases to evaluate your agent’s performance by either generating them with AI or uploading your own scenarios. AI-generated test cases offer two data options: generating based on subagents and actions, or generating from knowledge available to the agent via the Agentforce Data Library.
            4. Choose Evaluations
              Evaluations measure your AI agent’s performance across key areas. Default evaluations include response accuracy, subagent assertion, and action assertion. To better match your testing goals, you can add quality-focused evaluations like completeness, coherence, conciseness, latency, and instruction adherence. Selecting the right mix of evaluations gives you the insights you need to strategically refine and improve your agent.

            See Also

             
            Loading
            Salesforce Help | Article