Salesforce Docs Portal

Agent Script Reference

Use this reference to look up Agent Script syntax, keywords, and concepts. For common patterns and examples, see Agent Script Patterns.

note: Beginning in April 2026, agent topics are now called subagents. There are no changes to functionality. During this transition, you may see a mix of the new and previous terms in our documentation

Syntax

This table lists some of the key terms used in an Agent Script file.

Symbol Description More Info
# Single-line comment. For example: # This is a comment Comments
... Slot-fill token that instructs the LLM to set the value. For example: with order_id = ... Variables, Utils
-> Begins logic instructions. For example: instructions: -> if @variables.verified: Reasoning Instructions
| Begins prompt instructions. For example: | Help the customer with their order. Reasoning Instructions
{!expression} Resolve a variable or resource in prompt instructions. For example: {!@variables.promotion_product} Reasoning Instructions
==, !=, <, >, is None, etc. Comparison operators. For example: @variables.count > 0 Supported Operators
@actions.name Reference an action. For example: run @actions.get_order Actions
@outputs.name Reference an action's output value. For example: set @variables.status = @outputs.status Actions
@subagent.name Delegate to another subagent. For example: consult: @subagent.specialist Tools
@utils.escalate Define a tool that escalates to a human service rep. For example: escalate: @utils.escalate Utils
@utils.setVariables Define a tool that instructs the LLM to set variable values. For example: set_name: @utils.setVariables Utils
@utils.transition to Define a tool that transitions to a different subagent. For example: @utils.transition to @subagent.Order_Management Utils
@variables.name Reference a variable from logic instructions. For example: @variables.order_id Variables
actions Define agent actions or tools available from a subagent. Actions, Tools
after_reasoning Run logic after the reasoning loop exits. After Reasoning
available when Conditionally show or hide a tool. For example: available when @variables.verified == True Tools
config Top-level block for agent configuration. Config Block
connection Top-level block for external connections like Enhanced Chat. For example: connection messaging: Connection Block
if / else Conditional branching. For example: if @variables.is_member == True: Conditional Expressions
instructions Guidance for the LLM within system or reasoning blocks. Reasoning Instructions
language Top-level block for supported languages. Language Block
linked Declare a variable whose value comes from an external source. For example: session_id: linked string Variables
messages System messages like welcome and error prompts. System Block
modality voice Top-level block that defines how an Agentforce Voice agent speaks, including the voice persona and voice model. Configure Voice Models
mutable Allow a variable's value to be changed. For example: order_id: mutable string = "" Variables
reasoning Block containing instructions and tools for the LLM. Reasoning Instructions
reasoning.actions Tools the LLM can choose to call within a subagent. Tools (Reasoning Actions)
reasoning.instructions Prompt and logic instructions sent to the reasoning engine. Reasoning Instructions
run Execute an action deterministically. For example: run @actions.get_order Actions
set Store a value in a variable. For example: set @variables.status = @outputs.status Variables, Actions
start_agent Entry point block for subagent classification and routing. For example: start_agent agent_router: Start Agent Block
system Top-level block for agent instructions and messages. System Block
system.instructions Override system instructions for a specific subagent. System Overrides
target The flow or action target for an agent action. For example: target: "flow://Get_Order" Actions
subagent Top-level block defining a subagent's instructions and actions. For example: subagent Order_Management: Subagent Blocks
topic Deprecated. Use subagent instead. Subagent Blocks
transition to Move to a different subagent from logic instructions. For example: transition to @subagent.wrap_up Utils
variables Top-level block for global agent variables. Variables
with Bind an input parameter. For example: with order_id = @variables.order_id Actions

Concepts

These reference topics cover key concepts and terms associated with Agent Script.

  • Actions - Define executable tasks that an agent can perform, such as running a flow or transitioning to a new subagent.

  • After Reasoning - Optional block inside a subagent that runs after the reasoning loop exits.

  • Blocks - The structural components of an Agent Script, where each block contains a set of properties that describe data or procedures.

  • Conditional Expressions - Deterministically specify what actions to take or which prompts to include based on the current context.

  • Configure Voice Models - Select and configure the text-to-speech voice model for an Agentforce Voice agent using the modality voice block.

  • Reasoning Instructions - Instructions that Agentforce resolves into a prompt for the LLM.

  • Start Agent Block - A special subagent used for subagent classification, filtering, and routing.

  • Supported Operators - The comparison, logical, and arithmetic operators you can use in Agent Script.

  • Tools (Reasoning Actions) - Executable functions that the LLM can choose to call, based on the tool's description and current context.

  • Subagents - A set of instructions, actions, and reasoning that defines a job that an agent can do.

  • Utils - Utility functions used as tools, such as transitioning to subagents or setting variable values.

  • Variables - Let agents track information across conversation turns.