Lesson 19 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 4 · AI Agents · 35% of exam

4.4 Agentforce Builder: Canvas and Script Views

3 min read Updated Nov 16, 2026

Exam objective

Explain the purpose of Canvas and Script views in Agentforce Builder and how builders use them to inspect, configure, and validate an agent.

Canvas view for visual configuration

Canvas view presents Agent Script as readable blocks and configuration panels. It helps a builder understand the agent’s definition, routing, subagents, actions, variables, and instructions without starting from a code editor. Canvas supports common configuration tasks and quick actions for adding resources or logic. It is useful when reviewing an agent’s structure, editing natural-language instructions, or configuring common conditions. The visual representation does not mean the agent is a simple flowchart; it is a view of a script-backed agent with both language instructions and programmatic behavior.

Script view for direct editing

Script view lets advanced users inspect and edit Agent Script directly. Salesforce describes developer aids such as syntax highlighting, autocompletion, and validation. Direct editing can be useful for reviewing expressions and transitions, making precise changes, or understanding control flow across several components. A builder should still know the business meaning of the script before modifying it. A syntactically valid expression can still implement the wrong policy. Use comments or clear names where supported, keep conditions readable, and validate the outcome in preview after edits.

The views stay synchronized

Canvas and Script are two ways to work with the same agent configuration. Salesforce states that configuration and edits are consistent across views. A builder can use Canvas to inspect the broad design, then use Script to review logic in detail, or edit script and return to Canvas to confirm that resources and behavior are represented as intended. The Explorer provides an inventory of agent elements, while Preview lets the builder try utterances and inspect what the agent selected. The Console can surface errors and warnings such as syntax problems or unexpected values. These features support a review loop; they do not replace scenario testing. A practical review workflow

Before editing, identify the user outcome and the part of the agent that controls it. Inspect the relevant subagent or topic, instructions, actions, variables, filters, and transitions. Use Canvas for configuration clarity and Script for expression detail. Preview a normal request and at least one boundary case. If the change affects action inputs or conditions, confirm that values are populated as expected. Look at the interaction details or trace to see which subagent and action were selected. Save draft changes, resolve warnings that could affect behavior, and follow the organization’s version and activation process before making the agent available to users.

TIP: Use Canvas to understand and configure the agent visually, Script to inspect precise logic, and Preview or trace to verify what happens for an actual utterance.

The exam guide explicitly expects understanding of how Agent Script functions in Canvas and Script view; screen labels may change between releases.

Extra concept: A Preview trace can reveal whether a problem came from routing, instructions, an action, or response generation.

Official references:

  • Agent Script https://help.salesforce.com/s/articleView?id=ai.agent_script.htm&language=en_US&type=5
  • Explore Agentforce Builder https://help.salesforce.com/s/articleView?id=ai.agent_builder_tour.htm&language=en_US&type=5
  • Building Agents in Canvas View https://help.salesforce.com/s/articleView?id=ai.agent_canvas.htm&language=en_US&type=5

Key takeaways

  • Canvas summarizes the script-backed configuration in an approachable editor.
  • Script view offers direct editing and aids for expressions and logic.
  • The views stay consistent; inspect, preview, and validate changes before deployment.

Check your knowledge

Answer exam-style AI Agents questions with answers and explanations.

Practice AI Agents
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