CivicAid AI

Inspiration

Government schemes are designed to help citizens, but discovering the right scheme can be difficult. Information is often scattered across different sources, eligibility criteria can be confusing, and citizens may not know which documents they need.

We wanted to build something that could turn this complicated process into a simple, personalized experience. This led us to CivicAid AI — an AI-powered civic assistant designed to help people find relevant government schemes and understand their eligibility.

What it does

CivicAid AI allows users to provide information about their personal situation, such as age, income, location, occupation, and needs.

The system then analyzes the user's profile against available schemes and provides:

• Personalized scheme recommendations
• Eligibility matching
• An explainable CivicAid Score
• Reasons why a user matches a scheme
• Missing document identification
• Clear next-step guidance
• A simple and accessible interface

Instead of only telling users which schemes exist, CivicAid focuses on helping them understand what they can potentially access and what they should do next.

How we built it

We built CivicAid AI as a web-based application using Python and Flask for the backend, with HTML, CSS, and JavaScript for the user interface.

The core intelligence combines rule-based eligibility checking with NLP-based matching. We use TF-IDF and cosine similarity to compare a user's needs and profile information with scheme descriptions.

A weighted scoring system combines different eligibility factors to generate an explainable CivicAid Score. The system also main

Built With

• ai
• data
• natural-language-processing
• python
• streamlit