Projects using Python in KarachiProjects using Python in Karachi
Projects
People
Cover image for Built a full-stack HRMS in
Built a full-stack HRMS in under 2 weeks as a side project to dive deeper into Python and backend development! Features so far: Employee management with role-based access (Admin / HR / Employee) Leave request workflow with approval/rejection Attendance tracking — clock in/out, monthly calendar view Payroll engine — tax brackets, overtime, pro-rated salary, PDF payslip download Notifications, search, pagination, CSV exports Dockerized and deployed Stack: Next.js · TypeScript · Tailwind · FastAPI · PostgreSQL · SQLAlchemy The backend was a new challenge for me: SQLAlchemy relationships, Alembic migrations, Decimal precision for payroll calculations, streaming PDF responses — all of it was tricky at first, but I’ve learned a lot along the way. URL: https://lnkd.in/dRg86PtQ (https://lnkd.in/dRg86PtQ)This is just the beginning! I plan to add many more features.
0
49
Cover image for QueryMind lets you query a
QueryMind lets you query a real database using plain English. Type a question, get an answer — no SQL knowledge needed. Built a production-grade AI agent using LangGraph that converts natural language to SQL, executes it on a real PostgreSQL database with 100,000+ rows, and automatically corrects errors in a retry loop if the query fails. Key features: 7-node LangGraph agent with conditional routing and self-correction pgvector semantic search for intelligent schema retrieval Full observability dashboard with real-time metrics and query history Trace replay — see every step the agent took to answer your question Deployed live: Next.js frontend on Vercel, FastAPI backend on Render Tech: LangGraph · Groq LLaMA 3.3 70B · PostgreSQL · pgvector · FastAPI · Next.js · Tailwind CSS Github: https://github.com/moiz-mansoori/QueryMind-NL2SQL-Agent-System
0
21
Cover image for From Chaos to 2,400 Bookings:
From Chaos to 2,400 Bookings: How an AI Agent Transformed a Medical Clinic's Lead Conversion A few months ago, a medical clinic came to me with a problem that looked manageable on the surface, but was quietly killing their ROI. They were receiving 1,000+ inbound messages per day from marketing traffic. Patients ready to book. Leads that had already raised their hand. And they were handling all of it with 3 human agents. The Reality of the "Before" The agents weren't lazy. The system was just broken by design. Messages piled up and were answered in bulk, every few hours No 24/7 coverage large windows of zero response First response times were painfully slow Inconsistency was the norm different answers, missed context, dropped conversations The ROI was low. Sometimes negative. When a patient is ready to book and no one answers for 4 hours, they move on. That's not a people problem. That's a systems problem. What I Built I deployed an AI agent purpose-built for their intake and appointment booking workflow. No ramp-up time. No shift changes. No bulk-reply backlogs. ⚡ Instant response to every single message 🕐 24/7 coverage — midnight, weekends, holidays 📋 Consistent, accurate information every time 🔁 Seamlessly handles volume spikes without degradation The Results (First 2 Months) → 2,200+ appointments booked → 2,000+ new patients created → 2,400+ total bookings and climbing The same volume of leads. The same marketing spend. Completely different outcome. The only variable that changed was response speed and consistency. The Lesson Lead conversion in healthcare isn't just a sales problem, it's a response infrastructure problem. Patients contacting a clinic are often anxious, time-sensitive, and comparison shopping. The practice that answers first, clearly, and at any hour wins the appointment. AI didn't replace the care the clinic provides. It just made sure no one ever had to wait to get through the door.
1
47