Struct Agent 

pub struct Agent {
    pub name: String,
    pub instructions: Option<Instructions>,
    pub model: String,
    pub tools: Vec<Arc<dyn Tool>>,
    pub handoffs: Vec<Agent>,
    pub model_settings: ModelSettings,
    pub handoff_description: Option<String>,
}

An AI agent configured with instructions, tools, and settings

Agents are the core abstraction for building AI applications. They encapsulate a model, system prompt (instructions), tools, and other configuration.

Fields

name: String

The name of the agent

instructions: Option<Instructions>

Instructions (system prompt) for the agent

model: String

The model to use (e.g., “gpt-4”, “claude-3-5-sonnet”)

tools: Vec<Arc<dyn Tool>>

Tools available to the agent

handoffs: Vec<Agent>

Handoff agents (sub-agents the agent can delegate to)

model_settings: ModelSettings

Model settings (temperature, max_tokens, etc.)

handoff_description: Option<String>

Description for when this agent is used as a handoff

Implementations

impl Agent

pub fn new(name: impl Into<String>) -> Self

Create a new agent with the given name

pub fn builder(name: impl Into<String>) -> AgentBuilder

Create a builder for the agent

pub fn clone_with(&self) -> AgentBuilder

Clone the agent with modifications

pub fn system_prompt(&self) -> Option<&str>

Get the system prompt for the agent

pub async fn run( &self, input: impl Into<String>, config: &RunConfig, ) -> Result<RunResult>

Run the agent with the given input

This is a convenience method that creates a default RunConfig. For more control, use Runner::run directly.

pub fn with_tool(self, tool: impl Tool + 'static) -> Self

Add a tool to the agent

pub fn with_handoff(self, agent: Agent) -> Self

Add a handoff agent

Trait Implementations

impl Clone for Agent

fn clone(&self) -> Agent

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Agent

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.