Loading
Agentforce and Einstein Generative AI
Содержание
Фильтровать по (0)Добавить
Выбрать фильтры

          Результаты отсутствуют
          Результаты отсутствуют
          Ниже приведены некоторые советы по поиску.

          Проверьте орфографию ключевых слов.
          Воспользуйтесь более общим поисковым запросом.
          Выберите несколько фильтров для расширения области поиска.

            Выполните поиск по всей справке Salesforce.
            Выполните поиск по всей справке Salesforce.
            Test Agents

            You are here:

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

            Test Agents

            Test your AI agents at scale with a flexible, AI-driven testing workflow in Agentforce Studio Testing Center. Build test suites, generate test cases, and run evaluations across many scenarios at once in a spreadsheet-inspired interface designed to help you validate and debug agent conversations.

            Required Editions

            green checkmark

            This article applies to:

            		 New Testing Center in Agentforce Studio (Beta)
            red crossmark

            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.

            Testing agents in Agentforce Studio Testing Center lets you simulate conversations at scale and evaluate how your agent responds across many inputs at once. Instead of testing one scenario at a time, you build a test suite, provide test cases, and run the whole set together. Scorers automatically evaluate each response so you can quickly identify where your agent is falling short before it reaches users.

            To build test cases, you can fast-track with AI-generated scenarios based on your agent's specific subagents and actions, or use data linked through an Agentforce Data Library. You can also manually craft and upload your own test cases, or automate test runs using the Testing Center API to integrate testing into your development workflow.

            After generating test cases, select from built-in scorers or develop custom scorers tailored to your business needs. Track test history and manage all your test suites from the same spreadsheet-inspired interface.

            • Create a Test Suite
              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 via an Agentforce Data Library.
            • Define Test Conditions
              When you upload test cases from the CSV template, defining test conditions such as conversation history and context variables helps provide context. These variables help simulate more realistic user interactions, making your tests more reliable and reflective of actual agent behavior.
            • Select Your Test Data
              Evaluate your agent’s performance by using AI-generated tests cases or uploading your own test cases in a CSV template. AI-generated test cases offer two data options: generating tests based on subagents and actions, or generating tests based on the knowledge available to the agent via an Agentforce Data Library.
            • 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.
             
            Загрузка
            Salesforce Help | Article