Code Node

​

Code Node vs Custom Function

​

Write Your Code

1

Add a Code Node

Click the Code node from the left sidebar to add it to the canvas.

2

Open the code editor

Click Open on the code node to launch the code editor.

3

Write JavaScript

Write your JavaScript code in the editor. You have access to dynamic variables, call metadata, and the fetch function for HTTP requests. See JavaScript Environment below for details.

Copy

Ask AI

// Example: look up an order and return the status
const response = await fetch("https://api.example.com/orders/" + dv.order_id);
const data = await response.json();
return { status: data.status, estimated_delivery: data.delivery_date };

4

Set response variables (optional)

Use Store Fields as Variables to extract values from your code’s return value and save them as dynamic variables. Specify a variable name and the JSON path to the value.For example, if your code returns { "status": "shipped", "estimated_delivery": "March 25" }:

Variable Name	JSON Path	Extracted Value
order_status	status	"shipped"
delivery_date	estimated_delivery	"March 25"

These variables can then be referenced as {{order_status}} and {{delivery_date}} in other nodes.

5

Test your code

Click Run Code at the bottom of the editor to test. Use the Dynamic Variables dropdown in the editor to set test values for your variables (e.g., give customer_name a value of “John Doe”) — these values are only used during testing and won’t affect your live agent. The output panel will show the result and any console.log() output.

​

JavaScript Environment

​

dv — Dynamic Variables

const name = dv.customer_name;       // "John Doe"
const orderId = dv.order_id;         // "78542"
const total = parseFloat(dv.amount); // Convert to number if needed

​

metadata — Call Metadata

const customerId = metadata.customer_id;
const priority = metadata.priority_level;

​

fetch(url) — HTTP Requests

// GET request
const response = await fetch("https://api.example.com/data");
const data = await response.json();

// POST request
const response = await fetch("https://api.example.com/submit", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ name: dv.customer_name })
});

​

console.log() — Debugging

console.log("Customer:", dv.customer_name);
console.log("API response:", JSON.stringify(data));

​

Examples

​

Format data from dynamic variables

// Combine and format customer info
const fullName = dv.first_name + " " + dv.last_name;
const summary = `Customer ${fullName} (ID: ${dv.customer_id}) requested a callback.`;
return { full_name: fullName, summary: summary };

​

Fetch data from an external API

// Look up order status from your API
const response = await fetch("https://api.example.com/orders/" + dv.order_id, {
  headers: { "Authorization": "Bearer " + dv.api_token }
});
const order = await response.json();
return {
  status: order.status,
  items: order.items.length,
  total: "$" + order.total.toFixed(2)
};

​

Conditional logic with API call

// Route based on customer tier
const response = await fetch("https://api.example.com/customers/" + dv.customer_id);
const customer = await response.json();

if (customer.tier === "premium") {
  return { action: "priority_support", wait_time: "0 minutes" };
} else if (customer.tier === "standard") {
  return { action: "standard_queue", wait_time: "5 minutes" };
} else {
  return { action: "general_queue", wait_time: "10 minutes" };
}

​

Response Variables

​

When Can Transition Happen

• If Wait for Result is turned off:
  • If Speak During Execution is on, the agent transitions once done talking
  • If Speak During Execution is off, the agent transitions immediately after code starts running
  • If the user interrupts the agent, transition can happen once the user is done speaking
• If Wait for Result is turned on:
  • If Speak During Execution is on, the agent transitions once code finishes and agent is done talking
  • If Speak During Execution is off, the agent transitions once code finishes
  • If the user interrupts the agent, transition can happen once code finishes and user is done speaking

​

Node Settings

• Speak During Execution: When enabled, the agent says something while the code runs (e.g., “Let me check that for you.”). Choose between Prompt (LLM generates the message) or Static Text (exact text you provide).
• Wait for Result: When enabled, the agent waits for the code to finish before transitioning. This guarantees that when you reach the next node, the result and extracted variables are ready.
• Timeout: How long the code can run before timing out. Range: 5–60 seconds. Default: 30 seconds.
• Global Node: Read more at Global Node.
• Block Interruptions: When enabled, the agent will not be interrupted by the user when speaking.
• LLM: Choose a different model for this node. Used for speak during execution message generation if set to Prompt.
• Fine-tuning Examples: Can finetune transition. Read more at Finetune Examples.

​

FAQ