Skip to content

harshitha090/Agentic_AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

Agentic AI for Autonomous Enterprise Workflows

Overview

This project implements a multi-agent AI system that autonomously executes enterprise workflows with minimal human intervention.

The system demonstrates procurement-to-payment automation using intelligent agents that can plan, execute, monitor, and self-correct workflows while maintaining a complete audit trail.


Key Features

  • Autonomous workflow execution
  • Multi-agent collaboration
  • Failure detection & self-healing
  • Real-time workflow monitoring
  • Full audit trail (explainable decisions)
  • SLA tracking & escalation

System Architecture

Agents:

  • Orchestrator Agent – Manages workflow execution
  • Data Agent – Retrieves and validates data
  • Decision Agent – Selects best options
  • Execution Agent – Performs actions (APIs/mock)
  • Verification Agent – Validates completion
  • Monitoring Agent – Detects failures & SLA risks

Workflow Example (Procurement-to-Payment)

  1. Request validation
  2. Vendor selection
  3. Approval process
  4. Payment execution
  5. Verification

Tech Stack

Backend:

  • Python
  • FastAPI
  • SQLite

Frontend:

  • React (Vite)
  • Tailwind CSS
  • Axios

Project Structure

Agentic_AI/
├── backend/
├── frontend/
├── README.md

How to Run

Backend

cd backend
pip install fastapi uvicorn
uvicorn main:app --reload

Frontend

cd frontend
npm install
npm run dev

API Endpoints

Start Workflow

POST /start-workflow

{
  "item": "Laptop",
  "budget": 80000
}

Get Workflow Status

GET /workflow/{id}


Business Impact

  • 90% reduction in workflow time
  • Significant cost savings
  • Reduced manual errors
  • Faster decision-making
  • Improved SLA compliance

Use Cases

  • Procurement-to-Payment
  • Employee Onboarding
  • Contract Lifecycle Management
  • Meeting Intelligence Systems

Key Insight

“We are not just automating tasks — we are automating decision-making.”


Future Enhancements

  • Integration with real enterprise APIs
  • Advanced ML-based decision models
  • Predictive workflow optimization
  • Voice-based interaction

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors