PDF to Form Automation

Overview

Cua can be used to automate interactions between form filling and local file systems over any operating system. Cua let's you interact with all the elements of a web page and local file systems to integrate between the two.

This preset usecase uses Cua Computer to interact with a web page and local file systems along with Agent Loops to run the agent in a loop with message history.

Set Up Your Environment

First, install the required dependencies:

Create a requirements.txt file:

cua-agent
cua-computer
python-dotenv>=1.0.0

Install the dependencies:

pip install -r requirements.txt

Create a .env file with your API keys:

ANTHROPIC_API_KEY=your-anthropic-api-key
CUA_API_KEY=sk_cua-api01...

Create Your Form Filling Script

Create a Python file (e.g., form_filling.py) and select your environment:

import asyncio
import logging
import os
import signal
import traceback

from agent import ComputerAgent
from computer import Computer, VMProviderType
from dotenv import load_dotenv

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def handle_sigint(sig, frame):
    print("\n\nExecution interrupted by user. Exiting gracefully...")
    exit(0)

async def fill_application():
    try:
        async with Computer(
            os_type="linux",
            provider_type=VMProviderType.CLOUD,
            name="your-sandbox-name",  # Replace with your sandbox name
            api_key=os.environ["CUA_API_KEY"],
            verbosity=logging.INFO,
        ) as computer:

            agent = ComputerAgent(
                model="cua/anthropic/claude-sonnet-4.5",
                tools=[computer],
                only_n_most_recent_images=3,
                verbosity=logging.INFO,
                trajectory_dir="trajectories",
                use_prompt_caching=True,
                max_trajectory_budget=5.0,
            )

            tasks = [
                "Visit https://www.overleaf.com/latex/templates/jakes-resume/syzfjbzwjncs.pdf and download the pdf.",
                "Visit https://form.jotform.com/252881246782264 and fill the form from the information in the pdf."
            ]

            history = []

            for i, task in enumerate(tasks, 1):
                print(f"\n[Task {i}/{len(tasks)}] {task}")

                # Add user message to history
                history.append({"role": "user", "content": task})

                # Run agent with conversation history
                async for result in agent.run(history, stream=False):
                    history += result.get("output", [])

                    # Print output for debugging
                    for item in result.get("output", []):
                        if item.get("type") == "message":
                            content = item.get("content", [])
                            for content_part in content:
                                if content_part.get("text"):
                                    logger.info(f"Agent: {content_part.get('text')}")
                        elif item.get("type") == "computer_call":
                            action = item.get("action", {})
                            action_type = action.get("type", "")
                            logger.debug(f"Computer Action: {action_type}")

                print(f"✅ Task {i}/{len(tasks)} completed")

            print("\n🎉 All tasks completed successfully!")

    except Exception as e:
        logger.error(f"Error in fill_application: {e}")
        traceback.print_exc()
        raise

def main():
    try:
        load_dotenv()

        if "ANTHROPIC_API_KEY" not in os.environ:
            raise RuntimeError(
                "Please set the ANTHROPIC_API_KEY environment variable.\n"
                "You can add it to a .env file in the project root."
            )

        if "CUA_API_KEY" not in os.environ:
            raise RuntimeError(
                "Please set the CUA_API_KEY environment variable.\n"
                "You can add it to a .env file in the project root."
            )

        signal.signal(signal.SIGINT, handle_sigint)

        asyncio.run(fill_application())

    except Exception as e:
        logger.error(f"Error running automation: {e}")
        traceback.print_exc()

if __name__ == "__main__":
    main()

import asyncio
import logging
import os
import signal
import traceback

from agent import ComputerAgent
from computer import Computer, VMProviderType
from dotenv import load_dotenv

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def handle_sigint(sig, frame):
    print("\n\nExecution interrupted by user. Exiting gracefully...")
    exit(0)

async def fill_application():
    try:
        async with Computer(
            os_type="linux",
            provider_type=VMProviderType.DOCKER,
            image="trycua/cua-xfce:latest",  # or "trycua/cua-ubuntu:latest"
            verbosity=logging.INFO,
        ) as computer:

            agent = ComputerAgent(
                model="cua/anthropic/claude-sonnet-4.5",
                tools=[computer],
                only_n_most_recent_images=3,
                verbosity=logging.INFO,
                trajectory_dir="trajectories",
                use_prompt_caching=True,
                max_trajectory_budget=5.0,
            )

            tasks = [
                "Visit https://www.overleaf.com/latex/templates/jakes-resume/syzfjbzwjncs.pdf and download the pdf.",
                "Visit https://form.jotform.com/252881246782264 and fill the form from the information in the pdf."
            ]

            history = []

            for i, task in enumerate(tasks, 1):
                print(f"\n[Task {i}/{len(tasks)}] {task}")

                # Add user message to history
                history.append({"role": "user", "content": task})

                # Run agent with conversation history
                async for result in agent.run(history, stream=False):
                    history += result.get("output", [])

                    # Print output for debugging
                    for item in result.get("output", []):
                        if item.get("type") == "message":
                            content = item.get("content", [])
                            for content_part in content:
                                if content_part.get("text"):
                                    logger.info(f"Agent: {content_part.get('text')}")
                        elif item.get("type") == "computer_call":
                            action = item.get("action", {})
                            action_type = action.get("type", "")
                            logger.debug(f"Computer Action: {action_type}")

                print(f"✅ Task {i}/{len(tasks)} completed")

            print("\n🎉 All tasks completed successfully!")

    except Exception as e:
        logger.error(f"Error in fill_application: {e}")
        traceback.print_exc()
        raise

def main():
    try:
        load_dotenv()

        if "ANTHROPIC_API_KEY" not in os.environ:
            raise RuntimeError(
                "Please set the ANTHROPIC_API_KEY environment variable.\n"
                "You can add it to a .env file in the project root."
            )

        signal.signal(signal.SIGINT, handle_sigint)

        asyncio.run(fill_application())

    except Exception as e:
        logger.error(f"Error running automation: {e}")
        traceback.print_exc()

if __name__ == "__main__":
    main()

import asyncio
import logging
import os
import signal
import traceback

from agent import ComputerAgent
from computer import Computer, VMProviderType
from dotenv import load_dotenv

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def handle_sigint(sig, frame):
    print("\n\nExecution interrupted by user. Exiting gracefully...")
    exit(0)

async def fill_application():
    try:
        async with Computer(
            os_type="macos",
            provider_type=VMProviderType.LUME,
            name="macos-sequoia-cua:latest",
            verbosity=logging.INFO,
        ) as computer:

            agent = ComputerAgent(
                model="cua/anthropic/claude-sonnet-4.5",
                tools=[computer],
                only_n_most_recent_images=3,
                verbosity=logging.INFO,
                trajectory_dir="trajectories",
                use_prompt_caching=True,
                max_trajectory_budget=5.0,
            )

            tasks = [
                "Visit https://www.overleaf.com/latex/templates/jakes-resume/syzfjbzwjncs.pdf and download the pdf.",
                "Visit https://form.jotform.com/252881246782264 and fill the form from the information in the pdf."
            ]

            history = []

            for i, task in enumerate(tasks, 1):
                print(f"\n[Task {i}/{len(tasks)}] {task}")

                # Add user message to history
                history.append({"role": "user", "content": task})

                # Run agent with conversation history
                async for result in agent.run(history, stream=False):
                    history += result.get("output", [])

                    # Print output for debugging
                    for item in result.get("output", []):
                        if item.get("type") == "message":
                            content = item.get("content", [])
                            for content_part in content:
                                if content_part.get("text"):
                                    logger.info(f"Agent: {content_part.get('text')}")
                        elif item.get("type") == "computer_call":
                            action = item.get("action", {})
                            action_type = action.get("type", "")
                            logger.debug(f"Computer Action: {action_type}")

                print(f"✅ Task {i}/{len(tasks)} completed")

            print("\n🎉 All tasks completed successfully!")

    except Exception as e:
        logger.error(f"Error in fill_application: {e}")
        traceback.print_exc()
        raise

def main():
    try:
        load_dotenv()

        if "ANTHROPIC_API_KEY" not in os.environ:
            raise RuntimeError(
                "Please set the ANTHROPIC_API_KEY environment variable.\n"
                "You can add it to a .env file in the project root."
            )

        signal.signal(signal.SIGINT, handle_sigint)

        asyncio.run(fill_application())

    except Exception as e:
        logger.error(f"Error running automation: {e}")
        traceback.print_exc()

if __name__ == "__main__":
    main()

import asyncio
import logging
import os
import signal
import traceback

from agent import ComputerAgent
from computer import Computer, VMProviderType
from dotenv import load_dotenv

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def handle_sigint(sig, frame):
    print("\n\nExecution interrupted by user. Exiting gracefully...")
    exit(0)

async def fill_application():
    try:
        async with Computer(
            os_type="windows",
            provider_type=VMProviderType.WINDOWS_SANDBOX,
            verbosity=logging.INFO,
        ) as computer:

            agent = ComputerAgent(
                model="cua/anthropic/claude-sonnet-4.5",
                tools=[computer],
                only_n_most_recent_images=3,
                verbosity=logging.INFO,
                trajectory_dir="trajectories",
                use_prompt_caching=True,
                max_trajectory_budget=5.0,
            )

            tasks = [
                "Visit https://www.overleaf.com/latex/templates/jakes-resume/syzfjbzwjncs.pdf and download the pdf.",
                "Visit https://form.jotform.com/252881246782264 and fill the form from the information in the pdf."
            ]

            history = []

            for i, task in enumerate(tasks, 1):
                print(f"\n[Task {i}/{len(tasks)}] {task}")

                # Add user message to history
                history.append({"role": "user", "content": task})

                # Run agent with conversation history
                async for result in agent.run(history, stream=False):
                    history += result.get("output", [])

                    # Print output for debugging
                    for item in result.get("output", []):
                        if item.get("type") == "message":
                            content = item.get("content", [])
                            for content_part in content:
                                if content_part.get("text"):
                                    logger.info(f"Agent: {content_part.get('text')}")
                        elif item.get("type") == "computer_call":
                            action = item.get("action", {})
                            action_type = action.get("type", "")
                            logger.debug(f"Computer Action: {action_type}")

                print(f"✅ Task {i}/{len(tasks)} completed")

            print("\n🎉 All tasks completed successfully!")

    except Exception as e:
        logger.error(f"Error in fill_application: {e}")
        traceback.print_exc()
        raise

def main():
    try:
        load_dotenv()

        if "ANTHROPIC_API_KEY" not in os.environ:
            raise RuntimeError(
                "Please set the ANTHROPIC_API_KEY environment variable.\n"
                "You can add it to a .env file in the project root."
            )

        signal.signal(signal.SIGINT, handle_sigint)

        asyncio.run(fill_application())

    except Exception as e:
        logger.error(f"Error running automation: {e}")
        traceback.print_exc()

if __name__ == "__main__":
    main()

Run Your Script

Execute your form filling automation:

python form_filling.py

The agent will:

Download the PDF resume from Overleaf
Extract information from the PDF
Fill out the JotForm with the extracted information

Monitor the output to see the agent's progress through each task.

Next Steps

Learn more about Cua computers and computer commands
Read about Agent loops, tools, and supported model providers
Experiment with different Models and Providers
Join our Discord community for help

Was this page helpful?