🚀 AI-SalesGrid

🌟 Intelligent Sales Workflow Automation

Your AI Superpower in Sales for Enterprise - Real-Time AI Multi-Agent Sales Orchestrator

AI SalesGrid - Solution Overview | Technical Deployment Guide

📖 Overview

AI-SalesGrid is an innovative enterprise solution designed to revolutionize sales processes through real-time AI multi-agent orchestration. Leveraging the power of Google Cloud's Generative AI and Vertex AI Agent Builder, this system acts as an intelligent sales superpower, automating and optimizing complex sales workflows. It integrates deeply with CRM systems and various Google Cloud services to provide a seamless, scalable, and highly effective platform for sales teams.

The project focuses on building an agentic workflow to empower sales professionals, enabling them to close deals faster, personalize customer interactions, and gain actionable insights, ultimately enhancing overall sales efficiency and revenue.

✨ Features

🎯 Real-Time Multi-Agent Orchestration: Deploys and manages a network of specialized AI agents that collaborate to achieve sales objectives.
🧠 Generative AI Integration: Utilizes Google Cloud's Vertex AI to power advanced conversational capabilities, content generation, and intelligent decision-making for sales agents.
☁️ Google Cloud Platform (GCP) Native: Built to leverage GCP services like Vertex AI, Firestore, BigQuery, Cloud Storage, and Cloud Run for scalability, reliability, and performance.
📊 CRM Integration Readiness: Designed with architecture capable of integrating with existing CRM systems to enrich agent context and streamline data flow.
⚡ Enterprise-Grade Scalability: Engineered for high performance and scalability to meet the demands of large enterprise sales operations.
🔒 Secure & Compliant: Adheres to Google Cloud's robust security and compliance standards.
Automated Sales Workflow: Manages the entire sales journey from initial client inquiry to final reporting.
Client Requirement Analysis: Specialized solutionagent analyzes client needs and matches them with available company services, strictly adhering to a knowledge base.
Dynamic Pricing Generation: The pricingagent generates pricing, validating against predefined rules like discount limits, margin thresholds, and approval policies.
Formal Proposal Generation: proposalagent crafts professional proposals following company templates, incorporating solution and pricing details.
Comprehensive Risk Assessment: riskagent evaluates delivery timelines, margin risks, and compliance issues, providing a risk score.
Executive Summary Reporting: reportingagent generates concise executive summaries, formatted for CEO dashboards, detailing deal size, margin, risk, and approval status.
Google Vertex AI Search Integration: Sub-agents utilize VertexAISearchTool to query an internal knowledge base (company-rules-kb) for up-to-date company policies and service information.
Google Search Integration: The Head Account Manager can perform external searches using GoogleSearchTool for broader context.
Multi-Agent Orchestration: A root_agent (Head Account Manager) intelligently delegates tasks to various sub-agents for specialized processing.
Configurable AI Models: Agents are configured to use Google Gemini gemini-2.5-flash model.
Containerized Deployment: Provided Dockerfile for easy, consistent, and scalable deployment.

🖥️ Architecture

The system's architecture is detailed in the Architecture Diagram directory and the AI SalesGrid - Tech Deployment.pdf. It typically involves a serverless deployment on Google Cloud Run, orchestrating various AI agents and interacting with data stores like Firestore and BigQuery, and potentially external CRM systems.

📚 Tech Stack

Language: Python 3.11
Agent Framework: Google Agent Development Kit (ADK)
AI Platform: Google Vertex AI
Large Language Model (LLM): Google Gemini (specifically gemini-2.5-flash)
Search Tools: VertexAISearchTool, GoogleSearchTool
Containerization: Docker
Cloud Platform: Google Cloud Platform (for Vertex AI services, project salesgrid-ai)

🛠️ Tech Stack by Tech field

Backend & AI Core:

(Generative AI, Agent Builder)
Agentic Framework: (Inferred: e.g., LangChain, CrewAI, or custom built using ADK-Python)

Database & Storage:

DevOps & Deployment:

(for serverless deployment)

🚀 Quick Start

Follow these steps to get AI-SalesGrid up and running for development and deployment.

Prerequisites

Python 3.9+: The core agents are developed in Python.
Docker: Required for building and running the containerized application.
Google Cloud SDK (gcloud CLI): Necessary for authenticating and interacting with Google Cloud services.
Google Cloud Project: An active GCP project with billing enabled.
Service Account Key: A JSON key file with necessary permissions (e.g., Vertex AI User, Firestore Editor, BigQuery Data Editor, Cloud Run Developer).

Installation

Clone the repository

git clone https://github.com/fadynabil10/AI-SalesGrid.git
cd AI-SalesGrid

Navigate to the agents directory
```
cd agents
```
Install Python dependencies Assumes a requirements.txt exists in the agents/ directory.
```
pip install -r requirements.txt
```

Environment setup Create a .env file in the agents/ directory to configure Google Cloud settings and other necessary variables.

cp .env.example .env

Example .env content (customize with your actual values):

# Google Cloud Project ID
GCP_PROJECT_ID=your-gcp-project-id

# Google Cloud Region (e.g., us-central1)
GCP_REGION=your-gcp-region

# Path to your Google Cloud service account key file
# Set this environment variable for local development
GOOGLE_APPLICATION_CREDENTIALS=/path/to/your/service-account-key.json

# Optional: CRM API Key or other integration secrets
CRM_API_KEY=your-crm-api-key

Ensure GOOGLE_APPLICATION_CREDENTIALS points to your service account JSON key file.

Build the Docker image From the root AI-SalesGrid directory:
```
docker build -t ai-salesgrid .
```

Start Development (Local Container)

To run the AI-SalesGrid application locally using Docker:

docker run -p 8080:8080 \
  -e GOOGLE_APPLICATION_CREDENTIALS=/app/path/to/your/service-account-key.json \
  -v /path/to/your/service-account-key.json:/app/path/to/your/service-account-key.json:ro \
  -e GCP_PROJECT_ID=your-gcp-project-id \
  -e GCP_REGION=your-gcp-region \
  ai-salesgrid

Note: Adjust the GOOGLE_APPLICATION_CREDENTIALS path inside the container and the volume mount (-v) to match your service account key location.

The application should be accessible at http://localhost:8080.

If you Start Development on (GCP)

To run the AI-SalesGrid application on Cloud Run using Docker:

adk deploy cloud_run   --project=$GOOGLE_CLOUD_PROJECT   --region=$GOOGLE_CLOUD_LOCATION   --with_ui .

📁 Project Structure

AI-SalesGrid/
├── AI SalesGrid - Solution.pdf    # High-level overview and business case
├── AI SalesGrid - Tech Deployment.pdf # Detailed technical deployment guide
├── Architecture Diagram/          # Contains architectural diagrams
│   └── (e.g., architecture-diagram.png)
├── Dockerfile                     # Docker build instructions for the application
└── agents/                        # Core directory for AI agents and logic
    ├── .env.example               # Example environment variables
    ├── requirements.txt           # Python dependencies for the agents
    ├── (e.g., main.py)            # Main entry point for the agent orchestration
    └── (other agent modules)      # Python files defining various agents and their functions

Project Structure

└── AI-SalesGrid/
    ├── AI SalesGrid - Solution.pdf
    ├── AI SalesGrid - Tech Deployment.pdf
    ├── Architecture Diagram
    │   ├── 1- Main Archtiect.png
    │   ├── 2- Multi Agent Arch.PNG
    │   ├── 3- Advanced Multi Agent with CRM.png
    │   ├── 4- Core Componant for Vertex AI Builder.jpg
    │   ├── 5.png
    │   ├── 6.png
    │   ├── 7.png
    │   └── 8.png
    ├── Dockerfile
    └── agents
        └── ai-salesgrid

Project Index

AI-SALESGRID/

__root__

Dockerfile

agents

ai-salesgrid

agent.py

Architecture Diagram

1- Main Archtiect.png

Getting Started

Prerequisites

Before getting started with AI-SalesGrid, ensure your runtime environment meets the following requirements:

Programming Language: Python
Container Runtime: Docker

Installation

Install AI-SalesGrid using one of the following methods:

Build from source:

Clone the AI-SalesGrid repository:

❯ git clone https://github.com/fadynabil10/AI-SalesGrid

Navigate to the project directory:

❯ cd AI-SalesGrid

Install the project dependencies:

Using docker

❯ docker build -t fadynabil10/AI-SalesGrid .

Usage

Run AI-SalesGrid using the following command: Using docker

❯ docker run -it {image_name}

⚙️ Configuration

Environment Variables

The application relies on environment variables for sensitive information and configuration. A .env.example file is provided in the agents/ directory.

Variable	Description	Default	Required
`GCP_PROJECT_ID`	Your Google Cloud Project ID.		Yes
`GCP_REGION`	The Google Cloud region for services (e.g., `us-central1`).		Yes
`GOOGLE_APPLICATION_CREDENTIALS`	Path to the Google service account key file (local dev only).		Yes
`CRM_API_KEY`	API key for integrating with external CRM systems.		No
`PORT`	The port on which the application will listen.	`8080`	No

Google Cloud Permissions

Ensure your Google Cloud service account has the necessary IAM roles:

Vertex AI User
Cloud Firestore User (or appropriate editor/viewer roles)
BigQuery Data Editor (or appropriate editor/viewer roles)
Storage Object Admin (for Cloud Storage access)
Cloud Run Developer (for deployment to Cloud Run)

🔧 Development

Available Scripts

Assumes a typical Python application setup within the agents/ directory.

Command	Description
`pip install -r requirements.txt`	Installs all required Python dependencies.
`python agents/main.py`	Starts the development server/agent orchestration.
`docker build . -t ai-salesgrid`	Builds the Docker image for the application.
`adk deploy cloud_run .`	Builds Solution to work Live API

Development Workflow

Set up your Google Cloud Project and obtain a service account key.
Configure environment variables in the .env file within the agents/ directory.
Install Python dependencies using pip.
Run the main application script (e.g., python agents/main.py) or use the Docker run command as described in "Start Development (Local Container)".
Interact with the agents via the exposed API (if any) or observe agent behaviors through logs.

🚀 Deployment

AI-SalesGrid is designed for cloud-native deployment, primarily on Google Cloud Run using Docker containers.

Production Build

The Dockerfile in the root directory defines the production build process.

# Build the production Docker image
docker build -t gcr.io/your-gcp-project-id/ai-salesgrid:latest .

Replace your-gcp-project-id with your actual Google Cloud Project ID.

Deployment to Google Cloud Run

Authenticate Docker with Google Container Registry (GCR) or Artifact Registry
```
gcloud auth configure-docker
```

Push the Docker image to GCR/Artifact Registry

docker push gcr.io/your-gcp-project-id/ai-salesgrid:latest

Deploy to Google Cloud Run

gcloud run deploy ai-salesgrid \
  --image gcr.io/your-gcp-project-id/ai-salesgrid:latest \
  --platform managed \
  --region your-gcp-region \
  --allow-unauthenticated # Or specify appropriate authentication if needed
  --set-env-vars GCP_PROJECT_ID=your-gcp-project-id,GCP_REGION=your-gcp-region \
  --service-account=your-cloud-run-service-account@your-gcp-project-id.iam.gserviceaccount.com

Replace placeholders with your actual project ID, region, and a service account with Cloud Run Invoker permissions for the deployed service.

Refer to AI SalesGrid - Tech Deployment.pdf for more detailed deployment instructions.

📚 API Reference

The AI-SalesGrid, being an orchestrator, may expose a RESTful API for external systems or UI clients to interact with the multi-agent system.

Base URL

The API base URL will be the endpoint provided by your Cloud Run service (e.g., https://ai-salesgrid-xxxxxx-uc.a.run.app).

Endpoints

Specific API endpoints would be detailed here based on the Python framework used (e.g., Flask, FastAPI) and the exposed agent functionalities.

Example (Hypothetical):

POST /api/v1/sales/engage: Initiates a new sales engagement workflow.
- Request Body: { "customer_info": {}, "product_details": {} }
- Response: { "engagement_id": "...", "status": "initiated" }
GET /api/v1/sales/engagement/{id}: Retrieves the status and progress of an ongoing engagement.
POST /api/v1/agent/task: Assigns a specific task to an agent or agent group.

🤝 Contributing

We welcome contributions to AI-SalesGrid! Please see our Contributing Guide for details on how to get started, report bugs, and suggest features.

Development Setup for Contributors

Contributors should follow the "Quick Start" guide for local development. Adherence to Python best practices, clear documentation of agent logic, and unit testing is highly encouraged.

🙏 Acknowledgments

Google Cloud Platform: For providing a robust suite of AI and cloud services.
Vertex AI & Generative AI: Powering the intelligence of the sales agents.
Open Source Community: For the vast array of Python libraries and tools that make this project possible.

📞 Support & Contact

🐛 Issues: GitHub Issues
💬 Discussions: GitHub Discussions
💡 Submit Pull Requests: Review open PRs, and submit your own PRs.

Contributing Guidelines

Fork the Repository: Start by forking the project repository to your github account.
Clone Locally: Clone the forked repository to your local machine using a git client.
```
git clone https://github.com/fadynabil10/AI-SalesGrid
```
Create a New Branch: Always work on a new branch, giving it a descriptive name.
```
git checkout -b new-feature-x
```
Make Your Changes: Develop and test your changes locally.
Commit Your Changes: Commit with a clear message describing your updates.
```
git commit -m 'Implemented new feature x.'
```
Push to github: Push the changes to your forked repository.
```
git push origin new-feature-x
```
Submit a Pull Request: Create a PR against the original project repository. Clearly describe the changes and their motivations.
Review: Once your PR is reviewed and approved, it will be merged into the main branch. Congratulations on your contribution!

Contributor Graph

⭐ Star this repo if you find it helpful!

Made with ❤️ by Fady Nabil

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
Architecture Diagram		Architecture Diagram
Demo		Demo
agents/ai-salesgrid		agents/ai-salesgrid
AI SalesGrid - Solution.pdf		AI SalesGrid - Solution.pdf
AI SalesGrid - Tech Deployment.pdf		AI SalesGrid - Tech Deployment.pdf
Dockerfile		Dockerfile
README.md		README.md

Folders and files

Latest commit

History

Repository files navigation

🚀 AI-SalesGrid

🌟 Intelligent Sales Workflow Automation

📖 Overview

✨ Features

🖥️ Architecture

📚 Tech Stack

🛠️ Tech Stack by Tech field

🚀 Quick Start

Prerequisites

Installation

Start Development (Local Container)

If you Start Development on (GCP)

📁 Project Structure

Project Structure

Project Index

Getting Started

Prerequisites

Installation

Usage

⚙️ Configuration

Environment Variables

Google Cloud Permissions

🔧 Development

Available Scripts

Development Workflow

🚀 Deployment

Production Build

Deployment to Google Cloud Run

📚 API Reference

Base URL

Endpoints

🤝 Contributing

Development Setup for Contributors

🙏 Acknowledgments

📞 Support & Contact

About

Topics

Resources

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages