Inshrah Fatima - AI Developer | ContraWork by Inshrah Fatima
Inshrah Fatima

Inshrah Fatima

"AI and ML Engineer |RAG Chatbots and Automation"

New to Contra

Inshrah is building their profile!

Followed by Jerry S and GALLERY L

Narowal, Pakistan

WorkPostsServicesAbout

Narowal, Pakistan

Cover image for I built and launched a
I built and launched a SaaS product on my own: TechNova AI. šŸš€ Every business gets its own private AI assistant that answers customer questions using only that business's own documents. What makes it different: šŸ”’ Every business has its own isolated workspace. Its documents, chat history and analytics are never mixed with anyone else's. šŸ“„ Upload PDFs, Word docs or text files šŸ“š Every answer shows which document it came from, and if the answer isn't in your documents, the AI says so instead of guessing šŸŒ Works in English, Urdu and Roman Urdu šŸ’¬ Add the assistant to your website with one line of code šŸ“Š Analytics show what customers ask and where the AI falls short Pricing: ā€¢ Free: 3 documents ā€¢ Standard: $19/month, 25 documents ā€¢ Premium: $49/month, unlimited documents Built with Next.js, TypeScript, Supabase (pgvector), Groq and Vercel. The AI was the easy part. Tenant isolation, PDF parsing in serverless and Urdu retrieval quality took the real work. I'm looking for my first few businesses to try the free plan and tell me honestly what to improve. If you answer the same customer questions again and again, message me. šŸ”— https://tech-nova-ai-saa-s.vercel.app #AI #RAG #SaaS #LLM #BuildInPublic #Pakistan #Startup
1
1
33
FreelancePro AI is an LLM-powered chatbot built to help freelancers with common freelancing questions and guidance. I developed it using Python, an LLM API, and Gradio, then deployed it on Hugging Face Spaces. The project demonstrates my skills in LLM integration, chatbot development, and AI application deployment.
1
57
Built and deployed TechNova RAG AI Assistant ā€” an intelligent document-based assistant that lets users ask questions about their documents and receive relevant, source-backed answers. The assistant uses Retrieval-Augmented Generation (RAG) to retrieve relevant information from uploaded documents before generating responses, helping reduce unsupported answers and making document search more useful. Key features: ā€¢ Document-based question answering ā€¢ RAG pipeline for contextual responses ā€¢ Source references with answers ā€¢ Conversation memory ā€¢ Casual English and Roman Urdu conversations ā€¢ AI assistant-style chat interface ā€¢ Streamlit deployment Tech Stack: Python ā€¢ RAG ā€¢ LLMs ā€¢ LangChain ā€¢ Vector Database ā€¢ Streamlit
1
52
Built an interactive Customer Churn Prediction ML App using Python, Scikit-learn, and Streamlit. šŸ¤–šŸ“Š The app predicts customer churn risk and helps businesses identify customers who may be likely to leave, enabling better customer retention decisions. šŸ”¹ Machine Learning šŸ”¹ Customer Churn Prediction šŸ”¹ Data Analysis šŸ”¹ Python & Scikit-learn šŸ”¹ Streamlit Deployment A practical ML project focused on turning customer data into actionable insights.
1
113