Freelancers using React Native in New DelhiFreelancers using React Native in New Delhi
Versatile Fullstack Engineer | Web & Mobile Expert
$50k+
Earned
5x
Hired
5.0
Rating
107
Followers
Versatile Fullstack Engineer | Web & Mobile Expert
Mobile App Architect • React Native Expert • 50+ App Shipped
$1k+
Earned
1x
Hired
5.0
Rating
14
Followers
Mobile App Architect • React Native Expert • 50+ App Shipped
Senior FullStack Developer
5.0
Rating
7
Followers
Senior FullStack Developer
Full Stack Developer
7
Followers
Full Stack Developer
Cover image for  AI Smart Call Assistance
AI Smart Call Assistance App Modern users struggle with spam calls, missed context, and inefficient call handling. We designed an AI-powered Smart Call Assistance experience inspired by intelligent call management systems like Hiya AI Phone, focusing on real-time call screening, transcription, and AI summaries to improve communication efficiency. Problem Statement (Users face): -- High volume of spam and unknown calls -- Lack of context during calls -- Difficulty remembering key points from conversations -- Inefficient call handling in professional workflows Solution: We designed a smart AI call assistant that helps users: > Identify and filter spam calls in real time > Generate automatic call transcripts > Provide AI-powered call summaries after every conversation > Highlight key action points and follow-ups Key Features 1. AI Call Screening: Detects spam and unknown callers instantly 2. Live Transcription: Converts speech to text during calls 3. Smart Summaries: Auto-generated call insights & decisions 4. Call Insights Dashboard: Stores past call history with searchable notes 5. Privacy-Focused Design: On-device processing and secure data handling UX focused Approach on: - Minimal interaction during calls (hands-free experience) - Clear visual hierarchy for call insights - Fast access to summaries post-call - Reducing cognitive load through automation Outcome: The concept demonstrates how AI can transform traditional calling into a productivity-first communication tool, reducing spam interference and improving decision-making speed.Or rewrite it in a more premium startup pitch tone
2
1
92
I craft modern digital experiences with design-driven code.
I craft modern digital experiences with design-driven code.
CSE student building ML pipelines & AI-powered products
New to Contra
CSE student building ML pipelines & AI-powered products
Cover image for What It Is
SevaFlow is a
What It Is SevaFlow is a civic complaint management system that lets Indian citizens file government complaints through Telegram without downloading any app or creating an account. The complaint gets automatically understood, routed, and tracked using AI. How It Works End to End A citizen sends a plain text message to the Telegram bot describing their problem. That message gets sent to Google Gemini with a carefully designed prompt at temperature 0.1, meaning the AI outputs consistent, deterministic JSON every time. Gemini extracts the issue type, location, responsible department, priority level, and generates a summary, all returning a confidence score between 0 and 1. The routing engine then takes over. It applies priority override rules first, so words like "fire" or "emergency" always trigger urgent regardless of what the AI said. It maps the AI suggestion to a configured department, assigns an SLA deadline based on department and priority, and stores everything in SQLite. The citizen immediately receives a Telegram confirmation with their reference ID like SF1234, department name, priority, and expected response time. The Admin Side Government officials log into a dashboard at the FastAPI server. They can filter and sort complaints, view the full status history of each one showing who changed what and when, update the status with notes like "team dispatched", and trigger a Telegram notification back to the citizen automatically. What Makes It Technically Interesting The AI pipeline has a two layer fallback. If Gemini fails, keyword matching kicks in to identify the department. If that also fails, it routes to General Services with medium priority and confidence marked as 0.0 so admins know it needs manual review. Nothing gets lost. The department configuration is fully data driven. Adding a new government department requires zero code changes, just a new entry in config.py (http://config.py) with keywords, SLA hours, and contact email. The system picks it up on restart. The database tracks two separate tables: complaints with all AI output stored alongside the raw text, and status history with a complete changelog including timestamps and the identity of who made each change. Why It Won Most hackathon civic tech projects build a web form. SevaFlow used Telegram as the interface because that is where citizens already are, made the AI classification reliable enough to actually route correctly, and built the full government side too, not just the submission side. End to end in one system, deployable on a single lightweight server.
0
23
Expert & Passionate Fullstack Engineer 8+ Years Experience
Expert & Passionate Fullstack Engineer 8+ Years Experience
Full-Stack Developer Building Scalable Web, Mobile
New to Contra
Full-Stack Developer Building Scalable Web, Mobile