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.

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.

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.

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

Use descriptive names for variables to make the workflow clear.
Add appropriate delays between actions to allow for page loading.
Handle errors gracefully by checking node verification results.
Use GPT-4 nodes to add flexibility and intelligence to your agents.
Leverage integrations like Google Sheets for data storage and sharing.
When using the python node, ensure all necessary libraries are imported.
For file operations in the add_data node, ensure file paths are correct and accessible.
When scheduling agents with the schedule node, use correct cron syntax.
For API calls, double-check URL, headers, and body parameters.
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.

​Key Concepts

POST /agents

​Agent Node Types

​Desktop+Browser Automation

​Data Processing

​Integrations

​Utility

Key Concepts

Agent Node Types

Desktop+Browser Automation

Data Processing

Integrations

Utility