Agentforce8% of the exam
Agentforce use cases, trust and agent permissions
Match a business need to the right Agentforce agent type or to deterministic automation, explain what the Einstein Trust Layer does, and troubleshoot agent access through the interacting user, the service agent user and the Manage AI Agents permission.
Describe the capabilities and use cases of Agentforce (scenarios about use cases, when it's appropriate to use AI, security, troubleshooting agent permissions).
~8 min read · 15 practice questions ·
What the exam expects
- Choose between an employee-facing agent and a customer-facing service agent from who the users are and which channel they use.
- Decide when a requirement suits generative AI and when it needs deterministic automation.
- Explain what the Einstein Trust Layer protects: zero data retention, secure data retrieval, prompt defense, toxicity detection, audit, and where data masking applies.
- State whose permissions employee and service agents run with.
- Troubleshoot an agent that is missing from Setup, refuses a request, or works for some users but not others.
Key facts
Editions
- Detail
- Enterprise, Performance, Unlimited, Developer with Foundations or Agentforce 1
Employee agent channels
- Detail
- Agentforce panel in Lightning Experience, Slack, Salesforce mobile app
Employee agent data access
- Detail
- Interacting user's permissions, sharing and field-level security
Service agent runs as
- Detail
- EinsteinServiceAgent User, Einstein Agent license and profile
Agent user default access
- Detail
- Minimal; expand with least privilege
Authenticated Experience Cloud customer
- Detail
- Agent runs as the logged-in site user
Enable prerequisite
- Detail
- Einstein Generative AI turned on first
Permission to enable and build
- Detail
- Manage AI Agents, which grants org-wide management of all agents
Data masking and agents
- Detail
- Disabled for agents to improve performance and accuracy
Topics renamed
- Detail
- Called subagents from April 2026, same functionality
Sources for this section (7)
- Agent Typeshelp.salesforce.com (opens in a new tab)
- Employee Agent Considerationshelp.salesforce.com (opens in a new tab)
- Einstein Trust Layerhelp.salesforce.com (opens in a new tab)
- Service Agent Accesshelp.salesforce.com (opens in a new tab)
- Enable Agentforcehelp.salesforce.com (opens in a new tab)
- Data Masking Limitationshelp.salesforce.com (opens in a new tab)
- Subagentshelp.salesforce.com (opens in a new tab)
- Which user record governs data access when an unauthenticated website visitor chats with a service agent?
- Why can't an agent instruction replace a validation rule for a mandatory field?
- Which Einstein Trust Layer services protect an agent conversation, and which one is disabled for agents?
- What should you check when Agents doesn't appear in Setup after buying Agentforce?
- Why is Manage AI Agents a sensitive permission to assign?
The questions are free to read. Answers with their sources and self-grading are included with the pack.
Keep reading with the Platform Administrator pack
- Core concepts
- Exam traps
- Worked scenario
The pack includes:
- All 28 lessons of the Platform Administrator guide, with reading progress
- Interactive decision walks and step-by-step sequence steppers
- Inline practice questions and one-click topic practice (15 questions for this lesson)
- An official source cited for every claim
- An AI tutor that answers from the guide
- Unlimited timed practice exams