Projects using Python in Lahore

Projects using Python in LahoreProjects using Python in Lahore

Cover image for From Fax to Brightree: Patient Intake for Healthcare Teams

From Fax to Brightree: Patient Intake for Healthcare Teams

0

7

Cover image for AI-Powered Voice Consultation Platform for Remote Healthcare

AI-Powered Voice Consultation Platform for Remote Healthcare

1

1

16

Cover image for Autonomous Multi-Agent Market Research System Development

Autonomous Multi-Agent Market Research System Development

3

12

Cover image for AI Function Calling Agent

AI Function Calling Agent

3

13

Cover image for Gemini MCP Server

Gemini MCP Server

0

5

Cover image for Promptly - AI System for Converting Ideas to Specs

Promptly - AI System for Converting Ideas to Specs

5

8

Cover image for In this project I wrote the AI strategy where people can sea...

In this project I wrote the AI strategy where people can search for any item allowed in the ESA Handbook, create compliant curriculum and ask to AI as well.

1

83

Havenly, A website for a national furniture brand , created with NEXT.js , DJANGO, FLASK , FAST API

1

211

Cover image for I helped streamline the lead-to-quotation

I helped streamline the lead-to-quotation process for a signage company. When a new lead comes in, we automatically use SerpAPI and RapidAPI to gather a list of potential vendors. Quotations are then requested from these vendors, submitted via email, and automatically extracted using Python. All leads, vendor info, and quotations are organized in Airtable, and the system intelligently selects the best quotation based on predefined criteria — all orchestrated seamlessly with Make.com (http://Make.com) automation.

1

100

Cover image for Athleads - Fitness Tracking Made Easy

Athleads - Fitness Tracking Made Easy

0

10

Cover image for AI-Powered Data Query Application

AI-Powered Data Query Application

0

1

Cover image for O-A: Predictive Demand Dashboard

O-A: Predictive Demand Dashboard

0

8

Cover image for Built a personalized LinkedIn post

Built a personalized LinkedIn post generator, and it's actually working end to end now. Most AI writing tools just take a prompt and spit out generic content. I wanted something different, a tool that understands who you are before it writes anything, and checks what's genuinely working on a topic right now instead of guessing. Here's what it actually does: → Personalized profile setup — set your niche, profession, key skills, and preferred tone once, it's reused for every post after that → Real-time research before writing — searches how people are actually discussing your topic right now, and extracts real patterns: hook style, structure, tone, without ever copying anyone's actual words → Fully personalized generation — combines your profile with the research patterns to write something original that sounds like you, not a generic AI voice → Editable output — every generated post is editable before you copy it, plus you get a breakdown of exactly which patterns informed the draft → Post history — every post you've generated is saved and browsable anytime → Fully self-contained build — Python, Streamlit, SQLite, no Supabase or external auth provider, just OpenRouter for generation and Serper for real-time research, with proper password hashing for authentication Still early, and currently invite-only while I manage access and costs on the research side. Link below, drop a comment or DM me for access. 🔗 https://post-pilot-ai.streamlit.app/ #AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) #Python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED) #Streamlit (https://www.linkedin.com/search/results/all/?keywords=%23streamlit&origin=HASH_TAG_FROM_FEED) #BuildInPublic (https://www.linkedin.com/search/results/all/?keywords=%23buildinpublic&origin=HASH_TAG_FROM_FEED) #OpenSource (https://www.linkedin.com/search/results/all/?keywords=%23opensource&origin=HASH_TAG_FROM_FEED) #MachineLearning (https://www.linkedin.com/search/results/all/?keywords=%23machinelearning&origin=HASH_TAG_FROM_FEED)

2

72

Cover image for I worked on MoolAI, an

I worked on MoolAI, an enterprise AI agent platform built for back-office SaaS workflows. The platform helps companies move from AI pilots to production-ready agents with proper governance, guardrails, workflow control, and deployment management. I focused on creating a clean, scalable, and business-friendly AI SaaS experience rather than a basic chatbot product.

0

87

Cover image for Kaizen is a Python learning

Kaizen is a Python learning platform for kids ages 12-14 — that specific age window matters because most coding-for-kids products target either much younger (Scratch/blocks) or much older (Codecademy-style courses for adults). The 12-14 zone is underserved: they've outgrown drag-and-drop blocks but they're not ready for "Watch this 2-hour video and take notes." The product is built around a narrative: the digital realm of Coderia is being corrupted, and the kid's job is to save it by writing real Python. Eight story realms (Echo Valley → Logic Peaks → Loop Lakes → ...), 94 lessons, one connected arc. Every lesson is real Python that runs, not blocks.

0

86

Cover image for Fraud and abuse detection wired

Fraud and abuse detection wired into a SIEM Card-testing and brute-force detection routed to on-call with a runbook attached to every alert. Who it was for: A payments platform exposed to automated card-testing traffic. The problem. Automated enumeration against payment endpoints is both a fraud loss and an availability threat, and it doesn't announce itself. Without detection it looks like ordinary traffic until the chargebacks arrive. What I did. Built the log pipeline into the SIEM, then wrote detections for card-testing patterns, brute force and anomalous transaction behaviour. Tuned edge rate-limiting and bot controls to cut volume at the perimeter. Every alert routes to on-call with a runbook attached, so whoever is paged at 3am has the next step in front of them. The result. Repeat attempts are caught as they start rather than reconstructed afterward, and response is a documented procedure instead of improvisation.

0

41