Autonomous Sales Agent

An AI sales enablement agent equipped with conversational objection handling playbooks, dynamic value pitch formulation, and automated contract proposal follow-ups.

---

Key Features

• Comprehensive: objection handling playbook covering budget, competition, and timing
• Dynamic: value proposition generation personalized to buyer industry
• Automated: post-call summary and custom proposal generation
• Next-best-action: guidance for enterprise sales representatives
• FastAPI: endpoint for real-time sales co-pilot assistance

---

Architecture

flowchart LR
    Objection([Buyer Objection]) --> API[Sales Agent]
    API --> Classifier[Objection Category]
    Classifier --> Playbook[(Objection Playbook DB)]
    Playbook --> Formulator[Response Formulator]
    Formulator --> Script[Tailored Counter-Pitch + Follow-up]

Loading

---

Tech Stack

Component	Technology	Purpose
Runtime	Python 3.12	Core execution environment
API Framework	FastAPI & Uvicorn	High-performance asynchronous REST endpoints
Data Validation	Pydantic v2	Strict schema validation and serialization
Execution Engine	Dual-Mode (Local + Cloud)	Production-ready logic with offline verification
Testing	Unittest & Pytest	Deterministic automated verification suite

---

Project Structure

sales-agent/
├── app/
│   ├── __init__.py
│   ├── api.py           # FastAPI routes and server definitions
│   ├── config.py        # Environment variables and application settings
│   ├── models.py        # Pydantic data schemas
│   └── services/        # Core business automation logic
├── tests/
│   ├── __init__.py
│   └── test_sales_agent.py   # Automated test suite
├── .env.example         # Template for environment configuration
├── .gitignore           # Python and runtime exclusions
├── LICENSE              # MIT License
├── README.md            # Comprehensive project documentation
└── requirements.txt     # Python package dependencies

---

Getting Started

Prerequisites

• Python 3.10+ (Python 3.12 recommended)
• pip package manager

Installation

1. Clone the repository:

   git clone https://github.com/erhatechnologiesai/sales-agent.git
   cd sales-agent

2. Create and activate a virtual environment:

   python -m venv venv
   # On Windows:
   venv\Scripts\activate
   # On macOS/Linux:
   source venv/bin/activate

3. Install dependencies:

   pip install -r requirements.txt

4. Configure environment variables:

   cp .env.example .env

---

Running the Application

Start the local development server with auto-reload:

python -m uvicorn app.api:app --reload --host 0.0.0.0 --port 8000

Once running, interactive documentation is accessible at:

• Swagger UI: http://127.0.0.1:8000/docs
• ReDoc: http://127.0.0.1:8000/redoc

---

API Endpoints

Method	Endpoint	Description
POST	/handle-objection	Analyze sales objection and retrieve tactical rebuttal

Example Request

curl -X POST http://127.0.0.1:8000/handle-objection -H "Content-Type: application/json" -d '{"objection": "Your solution is 30% more expensive than competitor X", "product": "Enterprise Cloud"}'

---

Running Tests

Execute the automated test suite:

python -m unittest tests/test_sales_agent.py

Or using pytest:

pytest tests/

All test cases are self-contained and run offline without requiring third-party API credentials.

---

Security & Best Practices

• Zero Credential Leakage: API tokens and secrets are loaded exclusively via environment variables and excluded by .gitignore.
• Strict Validation: All incoming request payloads are strictly validated using Pydantic schemas.
• Fail-Safe Fallbacks: Deterministic offline engines guarantee application continuity even during external provider outages.

---

License

This project is licensed under the terms of the MIT License.