DukaanAI

DukaanAI — An Open-Source AI Marketing Assistant for Local Shops

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

DukaanAI is an AI-powered marketing assistant designed to help local shopkeepers and small business owners create professional marketing content quickly and affordably.

Small businesses often struggle to write product descriptions, create WhatsApp promotions, and publish engaging social media posts while managing their daily operations.

DukaanAI aims to simplify this process by turning basic product information into ready-to-edit marketing content.

Key Features

• Generate product titles and descriptions.
• Create promotional messages for WhatsApp.
• Generate Instagram captions and hashtags.
• Support content creation in English, Hindi, and Punjabi.
• Copy and reuse generated marketing content.
• Help small businesses save time on repetitive marketing tasks.

Who Would Pay for It?

DukaanAI is designed for local retailers, clothing stores, electronics shops, and small business owners who need affordable marketing assistance without hiring a dedicated content writer.

A potential business model is a free trial followed by an affordable subscription.

How I Built It

DukaanAI is designed as a JavaScript-based web application powered by an open-weight AI model.

Technology Stack

• Frontend: React and Tailwind CSS
• Backend: Node.js and Express.js
• AI: An open-weight language model
• Inference: Local inference using Ollama, if used in the final implementation
• Version Control: Git and GitHub

How It Works

1. The user enters product details, such as the product name, price, and description.
2. The frontend sends the information to the backend.
3. The backend prepares a structured prompt for the AI model.
4. The model generates marketing content based on the supplied details.
5. The user reviews, edits, and copies the generated content.

The AI model is central to the application because generating useful marketing content is its primary functionality.

Model Name: Add the exact model name and license used in the project.

Why Does Open Innovation Matter?

Open innovation gives developers and small businesses more control over how they use AI.

For DukaanAI, open-weight models offer several potential advantages:

• Cost Control: Local inference can eliminate per-request API charges, although hardware, electricity, and hosting costs may still apply.
• Privacy: A fully local workflow can process product information without sending it to an external AI provider.
• Flexibility: Developers can experiment with different compatible models and choose the best balance between quality, speed, and resource requirements.
• Customization: Prompts and workflows can be adapted to specific business niches and regional languages.
• Reduced Vendor Lock-in: The application can be designed to support different models and inference providers instead of depending entirely on a single closed AI API.

Open-weight AI is not automatically better in every situation. Model quality, language support, licensing, and hardware requirements all matter.

The goal is to explore how open AI technology can make useful marketing assistance more accessible to small businesses.

My First User

The first step is to test DukaanAI with a local shopkeeper.

I plan to ask them to generate marketing content for real products and evaluate whether it saves time and produces useful results.

I want to understand:

• Does the generated content meet their needs?
• Which languages and promotional formats are most useful?
• Would they use the application regularly?
• Would they be willing to pay for it?

User Feedback: Add genuine feedback here after testing with a real user. Remove this section if you do not have user feedback yet.

---

Built with a simple goal: Make useful, accessible AI available to the small businesses that need it.