Talha Gohar - AI Chatbot Developer | Contra
Work by Talha Gohar
Sign Up
Post a job
Sign Up
Log In
Talha Gohar
Full-stack & AI developer building WhatsApp chatbots and LLM
Message
Follow
New to Contra
Talha is building their profile!
Followed by
GALLERY L
Islamabad, Pakistan
Work
Posts
About
Islamabad, Pakistan
0
WhatsApp AI Chatbot Title: AI WhatsApp Assistant for Clinics, Real Estate & Academies Description: Small businesses get most customer inquiries on WhatsApp and lose leads when replies are late. I built an AI chatbot that answers customers instantly in Roman Urdu and English. What I built: Demo flows for three verticals: clinics, real estate agents, and coaching academies FastAPI backend with LLM integration for natural replies A voice agent for hands-free inquiries An interactive phone-mockup demo so business owners can try it before buying Tools: Python, FastAPI, WhatsApp Business API, LLM APIs
0
13
0
JARVIS Title: JARVIS: Voice-First Autonomous AI Assistant Description: A locally hosted AI assistant that listens, reasons, and acts on my computer with human approval where it matters. What I built: Voice interface with a "Hey Jarvis" wake word, speech-to-text and text-to-speech Autonomous coding agent that locates, patches, tests, and fixes its own code Multi-provider LLM routing (Gemini, Groq, OpenRouter, Ollama, OpenAI) with automatic fallback 13 tools, approval gates, and an audit trail for safety n8n workflow automation and a REST/WebSocket API Tools: Python, FastAPI, LangChain, PostgreSQL, Redis, ChromaDB, Ollama, Docker, n8n
2
0
39
0
MedTwin Pro Title: Deep Learning Enhanced Digital Twin for Advance Biopsy System (FYP) Description: A final-year thesis project that connects AI, robotics, and a real-time 3D interface into one working system. What I built: DenseNet121 skin-lesion classifier: 87.6% accuracy and 0.915 AUC on HAM10000 4-DOF robotic arm on Raspberry Pi 4 with PCA9685 and MG996R servos Real-time digital twin in React and Three.js over WebSockets, about 47 ms latency FastAPI backend tying the model, hardware, and interface together Tools: Deep Learning, FastAPI, React, Three.js, WebSockets, Raspberry Pi
0
21
0
Portfolio Website Title: Full-Stack Portfolio with a Built-in AI Copilot Description: My personal portfolio, built as a real full-stack product, not just a static page. What I built: Floating AI Copilot chatbot using RAG and the Gemini API In-browser PDF resume viewer with zoom and fullscreen Category-filtered project grid with detail modals Contact form API and a Node/Express backend Tools: React, Vite, TypeScript, Tailwind CSS, Framer Motion, Node.js, Express
0
20
Challenges
Lovable Challenge
Rive Halloween Challenge
The invideo Editor Challenge
Challenges
Lovable Challenge
Rive Halloween Challenge
The invideo Editor Challenge