POST
/
get_next_step

This endpoint analyzes a screenshot and determines the next step needed to complete a given high-level task.

Request

high_level_task
string
required

Description of the overall task to complete (e.g. “Log into the application”)

screenshot
file
required

Current screenshot of the application

api_key
string
required

Your API key for authentication

history
string

Optional string containing previous steps taken

Response

Returns a string describing the next step to take to complete the task.

Example Request

curl -X POST https://u3mvtbirxf.us-east-1.awsapprunner.com/get_next_step \
  -F "high_level_task=Log into the application" \
  -F "screenshot=@current_screen.png" \
  -F "history=Step 1: Click login button\nStep 2: Enter username" \
  -F "api_key=your_api_key" \

Example Response

"Enter your email address in the email input field"