The Agents API now runs on every Open Agent Studio instance. An easy way to test this is to run Ngrok locally, or use Open Agent Studio which publishes a public IP address you can use as your personal Agents API. Agents API The website editor now generates a sample curl request in simple english with the JSON API for you to test. You can install ngrok to run the Agents API locally if you add /agents to the end of the ngrok address like in the above image. Agents API It even returns all the saved agent data during the automation, plus the verification testing loop steps we use to verify each action.

​
Key Concepts

Nodes: Individual actions an agent can perform Variables: Data that can be passed between nodes Verification: Checking if a node’s action was successful Global Variables: Shared data accessible across all nodes

POST /agents

Creates and runs a new agent based on the provided JSON configuration. Request Body 

{
  "key": "your_api_key",
  "json_output": [
    {
      "type": "action_type",
      "parameters": "action_specific_parameters"
    },
    ...
  ],
  "goal": "description_of_agent_goal"
}
Response Returns a string representation of the agent’s output data after executing all actions.

​
Agent Node Types

​
Desktop+Browser Automation

Delay Pauses execution for a specified time.
​
time
number
The time to pause in seconds 
json { "type": "delay", "time": 5 }
Keypress Types text or presses a key.
​
prompt
string
The text to type or key to press 
{ "type": "keypress", "prompt": "Hello, World!" }
Click Clicks on a specified target in english.
​
target
string
Description of element to click in simple language
​
browser_mode
boolean
Set to true for browser-specific clicks 
json { "type": "click", "target": "Submit button", "browser_mode": true }
Open Tab Opens a new browser tab.
​
target
string
URL to open 
json { "type": "open tab", "target": "https://www.example.com" }

​
Data Processing

GPT4 Uses GPT-4 for natural language processing.
​
prompt
string
System message for GPT-4
​
input
array
Array of input data keys
​
data
string
Output variable key 
json { "type": "gpt4", "prompt": "Summarize the following text:", "input": ["article_text"], "data": "summary" }
Python Executes custom Python code.
​
code
string
Python code to execute 
json { "type": "python", "code": "import pandas as pd\ndf = pd.read_csv('data.csv')\nprint(df.head())" }
Bash Executes bash commands.
​
command
string
Bash command to execute 
json { "type": "bash", "command": "ls -la" }

​
Integrations

Google Sheets Create Creates a new Google Sheet.
​
URL
string
Variable to store sheet URL
​
Sheet_Name
string
Variable to store sheet name 
json { "type": "google_sheets_create", "URL": "new_sheet_url", "Sheet_Name": "new_sheet_name" }
Google Sheets Add Row Adds a row to a Google Sheet.
​
URL
string
Sheet URL variable
​
Sheet_Name
string
Sheet name variable
​
data
array
Array of data to add 
json { "type": "google_sheets_add_row", "URL": "sheet_url", "Sheet_Name": "sheet_name", "data": ["John", "Doe", "30"] }
Google Sheets Read Reads data from a Google Sheet.
​
URL
string
Sheet URL
​
Sheet_Name
string
Sheet name
​
data
string
Variable to store read data 
json { "type": "google_sheets_read", "URL": "sheet_url", "Sheet_Name": "sheet_name", "data": "sheet_data" }
Email Sends an email.
​
to
string
Recipient email
​
subject
string
Email subject
​
body
string
Email body
​
data
string
Variable containing additional data to append 
json { "type": "email", "to": "recipient@example.com", "subject": "Monthly Report", "body": "Please find the monthly report attached.", "data": "report_data" }
API Makes an API call.
​
URL
string
API endpoint
​
headers
object
Request headers
​
body
object
Request body
​
data
string
Variable containing data to send
​
output
string
Variable to store response 
json { "type": "api", "URL": "https://api.example.com/data", "headers": {"Content-Type": "application/json"}, "body": {"key": "value"}, "data": "request_data", "output": "api_response" }

​
Utility

Add Data Loads data from various file types.
​
target
string
Variable to store data
​
data
string
File path 
json { "type": "add_data", "target": "csv_data", "data": "/path/to/file.csv" }
Schedule Schedules the agent to run at specified times.
​
cron
string
Cron expression for scheduling 
json { "type": "schedule", "cron": "0 9 * * 1-5" }
Generalized Agent Performs a generalized action based on a description using our state machine to solve open-ended problems.
​
description
string
Action to perform 
json { "type": "general", "description": "Search for the latest news articles about AI and summarize them" }
Semantic Scrape Scrapes data based on a semantic description.
​
target
string
Description of data to scrape
​
data
string
Variable to store scraped data 
json { "type": "semanticScrape", "target": "product reviews and ratings", "data": "product_reviews" }
Complete Example: Web Scraping and Data Processing Agent 
json { "key": "your_api_key", "json_output": [ { "type": "open tab", "target": "https://example.com/products" }, { "type": "delay", "time": 5 }, { "type": "semanticScrape", "target": "product listings", "data": "product_data" }, { "type": "gpt4", "prompt": "Analyze the product data and summarize the findings", "input": ["product_data"], "data": "analysis_result" }, { "type": "google_sheets_create", "URL": "sheet_url", "Sheet_Name": "sheet_name" }, { "type": "google_sheets_add_row", "URL": "sheet_url", "Sheet_Name": "sheet_name", "data": ["analysis_result"] }, { "type": "email", "to": "manager@company.com", "subject": "Product Analysis Report", "body": "Please find the latest product analysis attached.", "data": "analysis_result" } ], "goal": "Scrape product data, analyze it, save to Google Sheets, and email the results" }
Best Practices
  1. Use descriptive names for variables to make the workflow clear.
  2. Add appropriate delays between actions to allow for page loading.
  3. Handle errors gracefully by checking node verification results.
  4. Use GPT-4 nodes to add flexibility and intelligence to your agents.
  5. Leverage integrations like Google Sheets for data storage and sharing.
  6. When using the python node, ensure all necessary libraries are imported.
  7. For file operations in the add_data node, ensure file paths are correct and accessible.
  8. When scheduling agents with the schedule node, use correct cron syntax.
  9. For API calls, double-check URL, headers, and body parameters.
  10. Use the general node for complex actions that may require multiple steps.
By following this documentation, you can create sophisticated automated agents capable of handling a wide range of tasks across multiple platforms and services. The Agents API provides a flexible and powerful framework for defining complex sequences of actions, data processing, and integrations.