Lesson 29 of 41 · All lessons
Salesforce Agentforce Specialist
0 of 41 complete
1Exam Overview
  1. 1.1Agentforce Specialist Complete Exam Overview
2Prompt Engineering20%
  1. 2.1When to Use Prompt Builder
  2. 2.2Prompt Template Access Controls
  3. 2.3Field Generation and Flex Prompt Template Types
  4. 2.4Grounding Techniques for Prompt Templates
  5. 2.5Creating, Activating, and Executing Prompt Templates
  6. 2.6Best Practices for Writing Effective Prompts
  7. 2.7Trust Layer Security and Privacy Features
  8. 2.8Managing and Preventing Specific Models from Being Accessed
3Data 360 Fundamentals20%
  1. 3.1Agentforce Data Library
  2. 3.2Data 360 Concepts for Agentforce
  3. 3.3Chunking
  4. 3.4Indexing
  5. 3.5Retrievers
  6. 3.6Choosing a Grounding Approach for a Scenario
4AI Agents35%
  1. 4.1How an Agentforce Agent Works
  2. 4.2Agent Building Blocks and Agent Script
  3. 4.3Hybrid Reasoning and Deterministic Behavior
  4. 4.4Agentforce Builder: Canvas and Script Views
  5. 4.5Filters, Variables, and Template Expressions
  6. 4.6Standard and Custom Topics
  7. 4.7Standard and Custom Agent Actions
  8. 4.8Configure Topics, Instructions, and Actions for a Use Case
  9. 4.9Connecting Agents to Digital Experience, Email, Voice, and Slack
  10. 4.10Agent Security Context and Action Execution
  11. 4.11Choosing Between Employee and Service Agents
  12. 4.12When to Use Agent API
5Testing, Deployment, and Maintenance10%
  1. 5.1Testing Agents with Testing Center
  2. 5.2Understanding Testing Center Evaluations
  3. 5.3Deploying Agents from Sandbox to Production
  4. 5.4Deploying Prompt Templates Between Environments
  5. 5.5Reviewing Agent Behavior After Changes
6Governance and Observability10%
  1. 6.1Managing and Monitoring Agents
  2. 6.2Agent Analytics and Performance Signals
  3. 6.3Identifying Opportunities to Optimize Agent Behavior
  4. 6.4Using Observations to Guide Improvements
7Multi-Agent Orchestration5%
  1. 7.1Choosing a Multi-Agent Architecture
  2. 7.2Orchestrators and Connected Subagents
  3. 7.3Handoff and Supervisor Modes
  4. 7.4Model Context Protocol (MCP)
  5. 7.5Agent-to-Agent (A2A) Communication

Section 5 · Testing, Deployment, and Maintenance · 10% of exam

5.2 Understanding Testing Center Evaluations

3 min read Updated Nov 16, 2026

Exam objective

Explain how Testing Center evaluations assess routing, action selection, and response quality, and how to interpret test results.

Evaluations answer different questions

An evaluation, or scorer, measures a particular aspect of an agent’s behavior. Routing assertions ask whether the agent selected the expected topic or subagent. Action assertions check whether expected actions were selected or completed according to the test. Response evaluations assess whether the reply addresses the user’s need. Optional quality scorers can measure areas such as completeness, coherence, conciseness, instruction adherence, or latency. The exact names and availability depend on the Testing Center version and test type. Select measures that match the objective of the test rather than enabling every metric without a reason.

Expected responses and LLM judges

Some response evaluations use an LLM judge to compare the agent’s reply with an expected result and assign a score. Other evaluations may return pass/fail assertions for selected subagents or actions. Provide a useful expected response that states the facts or outcome that should be present. Do not turn the expected response into a list of evaluator instructions such as ‘be polite’ or ‘mention the order number’; Salesforce warns that mixing instructions into the expected answer can reduce scoring accuracy. Since generated wording can vary, evaluate the important content and behavior instead of demanding an exact sentence unless exact text is a genuine requirement. Read scores with context

A score is evidence about a test case, not a guarantee of production quality. Look at the scorer definition, the test utterance, expected result, actual response, selected subagent, and actions executed. A low response score may result from missing knowledge or an unclear expected answer. A failed action assertion might mean the agent did not use a required operation, or that the test case was configured with the wrong expected action. Repeated failures across related cases are more informative than a single isolated score. Use details and reasoning in the result panel to form a diagnosis, then manually reproduce the scenario in Builder.

Use evaluations to guide improvement

If routing assertions fail, refine descriptions, scopes, or deterministic transitions. If action assertions fail, inspect action availability, filters, instructions, inputs, and dependencies. If the response lacks accurate information, check grounding and source freshness. If the answer is factually correct but incomplete or inconsistent in tone, improve the relevant instructions and measure the same criterion again. Custom scorers can be useful for organization-specific requirements such as approved language or a defined compliance rule, but their criteria must be clear and tested. Establish acceptance thresholds before a release run, compare results with earlier versions, and investigate recurring gaps rather than optimizing one score in isolation.

TIP: Match the failed scorer to the symptom: routing, action selection, factual response, completeness, instruction adherence, or latency.

Default and optional evaluations vary between the newer Studio Testing Center and legacy Setup Testing Center. Check which scorer definitions apply to the test you are running.

Extra concept: Evaluation scores are most useful alongside the case details and trace; the number alone rarely identifies the root cause.

Official references:

  • Choose Evaluations https://help.salesforce.com/s/articleView?id=ai.agent_testing_center_evaluations.htm&language=en_US&type=5
  • Use Test Results https://help.salesforce.com/s/articleView?id=ai.agent_testing_center_use_test_results.htm&language=en_US&type=5
  • Select Scorers https://help.salesforce.com/s/articleView?id=ai.agent_studio_testing_center_evaluations.htm&language=en_US&type=5

Key takeaways

  • Scorers measure distinct behaviors such as routing, action choice, response quality, or latency.
  • LLM-judge response scores require a clear expected outcome and should allow acceptable wording variation.
  • Diagnose recurring failures with case details and traces, then rerun the affected tests.

Check your knowledge

Answer exam-style Testing, Deployment, and Maintenance questions with answers and explanations.

Practice Testing, Deployment, and Maintenance
Finished this lesson? Mark it complete to track your progress.

Ready for the real exam?

Take the timed Salesforce Agentforce Specialist simulator: same number of questions, same time limit.

Get Complete Access