All Toolsโ€บAI Workflow Builder
๐Ÿ”ง AI-Powered Automation ToolsMarch 21, 2026โœ… Tests passing

AI Workflow Builder

AI Workflow Builder allows developers to define and execute custom automation workflows by chaining AI model outputs (like Claude) with traditional tasks (e.g., API calls, data processing). It uses a declarative YAML configuration file to define the sequence of tasks, making it easy to create and modify workflows without writing additional code.

What It Does

  • Supports chaining AI model responses with other tasks
  • Declarative YAML-based workflow configuration
  • Built-in support for error handling and retries

Installation

1. Clone the repository:

git clone <repository-url>
   cd <repository-folder>

2. Install dependencies:

pip install -r requirements.txt

Usage

workflow:
  - name: "Generate AI Response"
    type: "ai_task"
    prompt: "What are the benefits of AI in healthcare?"
    model: "text-davinci-003"
    max_tokens: 100

Source Code

import yaml
import click
import openai
import logging
from typing import Any, Dict, List

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def execute_ai_task(task: Dict[str, Any]) -> str:
    """Executes an AI task using OpenAI's API."""
    try:
        prompt = task.get('prompt', '')
        model = task.get('model', 'text-davinci-003')
        max_tokens = task.get('max_tokens', 100)

        logger.info(f"Executing AI task with model {model} and prompt: {prompt}")
        response = openai.Completion.create(
            engine=model,
            prompt=prompt,
            max_tokens=max_tokens
        )
        return response.choices[0].text.strip()
    except Exception as e:
        logger.error(f"Error executing AI task: {e}")
        raise

def execute_workflow(config: Dict[str, Any]) -> List[Dict[str, Any]]:
    """Executes a workflow based on the provided configuration."""
    results = []
    for step in config.get('workflow', []):
        task_type = step.get('type')
        if task_type == 'ai_task':
            result = execute_ai_task(step)
            results.append({'step': step.get('name', 'Unnamed Step'), 'result': result})
        else:
            logger.warning(f"Unsupported task type: {task_type}")
            results.append({'step': step.get('name', 'Unnamed Step'), 'result': None, 'error': 'Unsupported task type'})
    return results

@click.command()
@click.option('--config', type=click.Path(exists=True), required=True, help='Path to the YAML configuration file.')
@click.option('--output', type=click.Path(writable=True), default=None, help='Optional path to save the workflow output.')
def main(config: str, output: str):
    """Main entry point for the AI Workflow Builder."""
    try:
        with open(config, 'r') as file:
            workflow_config = yaml.safe_load(file)

        logger.info("Loaded workflow configuration.")
        results = execute_workflow(workflow_config)

        if output:
            with open(output, 'w') as outfile:
                yaml.dump(results, outfile)
            logger.info(f"Workflow results saved to {output}")
        else:
            logger.info("Workflow results:")
            logger.info(results)

    except Exception as e:
        logger.error(f"Failed to execute workflow: {e}")

if __name__ == '__main__':
    main()

Community

Downloads

ยทยทยท

Rate this tool

No ratings yet โ€” be the first!

Details

Tool Name
ai_workflow_builder
Category
AI-Powered Automation Tools
Generated
March 21, 2026
Tests
Passing โœ…

Quick Install

Clone just this tool:

git clone --depth 1 --filter=blob:none --sparse \
  https://github.com/ptulin/autoaiforge.git
cd autoaiforge
git sparse-checkout set generated_tools/2026-03-21/ai_workflow_builder
cd generated_tools/2026-03-21/ai_workflow_builder
pip install -r requirements.txt 2>/dev/null || true
python ai_workflow_builder.py
AI Workflow Builder โ€” AI Tools by AutoAIForge