AI Agent Engineer Projects in LahoreAI Agent Engineer Projects in Lahore
Projects
People
Cover image for Meet AI is a video
Meet AI is a video conferencing SaaS where AI agents join live meetings as active participants and respond in real time. I built the full application stack. The hard part is the real-time layer. The backend provisions an AI agent the moment a meeting starts and keeps it running for the full call. Speech runs through a transcript pipeline and generates responses through the OpenAI API in near real time, so the agent replies while the conversation is still moving, not minutes later. After the meeting, the backend writes a structured summary through the same API, handled async by Inngest so nothing blocks the live app. The stack is Next.js 15 and React 19 with the Stream Video and Stream Chat SDKs, tRPC and Drizzle ORM on Neon PostgreSQL, and Better Auth across the stack. The platform runs 30 simultaneous live sessions, each with its own active AI agent, with no backend slowdown. What the client gets: live AI agents that take part in real meetings, plus automatic summaries, on a stack built to hold many sessions at once.
2
3
142
Cover image for French Legal AI Assistant &
French Legal AI Assistant & Agentic RAG System Overview I designed, built, and deployed a specialized Legal AI Assistant for French lawyers using agentic RAG, legal data pipelines, vector search, reranking, open-source LLMs, and citation-grounded answer generation. The system allowed lawyers to ask legal questions and receive answers grounded in French law articles, legal references, and relevant judicial cases. Problem / Challenge Legal data is very different from normal document data. A generic RAG pipeline using fixed-size chunks often breaks legal meaning, misses important context, or retrieves incomplete references. The main challenges were: 🔹 Legal documents had different structures and lengths 🔹 Articles and laws could not be randomly split into fixed-size chunks 🔹 Each answer needed traceable legal references 🔹 Retrieval had to understand legal scope, not just semantic similarity 🔹 The system needed to reduce hallucinations for legal users 🔹 Deployment had to respect privacy and regulatory requirements My Expertise I worked as the Lead AI Engineer / Agentic RAG Developer responsible for the complete system design and implementation. My responsibilities included: 🔹 Legal data pipeline architecture 🔹 Document parsing and preprocessing 🔹 Custom legal chunking strategy 🔹 Vector database design 🔹 Agentic RAG workflow development 🔹 Retrieval optimization and reranking 🔹 Open-source LLM deployment 🔹 Backend API development with FastAPI 🔹 Secure Azure cloud deployment 🔹 Multi-tenant system support French Legal Data Engineering Pipeline I built an automated ETL pipeline to process thousands of French legal documents, articles, and judicial cases. The pipeline handled: 🔹 Raw legal document ingestion 🔹 Text cleaning and normalization 🔹 Legal article extraction 🔹 Section-aware document structuring 🔹 Custom chunk generation 🔹 Metadata extraction for article number, article title, section, source, and reference 🔹 Embedding generation 🔹 Vector database ingestion 🔹 Repeatable updates for future legal data expansion The chunking strategy was designed so legal articles were not cut in the middle or separated from their meaning. Agentic RAG Workflow Instead of using a simple one-step vector search, I built a LangGraph-based agentic RAG workflow. The workflow included: 🔹 User query understanding 🔹 Legal intent detection 🔹 Legal domain and scope identification 🔹 Generation of 2–5 targeted legal search queries 🔹 Retrieval of relevant chunks for each query 🔹 Deduplication of repeated results 🔹 Reranking of retrieved legal evidence 🔹 Source-grounded answer generation This improved tested retrieval accuracy from around 50% to 95%+. Retrieval, Citations & Case Law The retrieval system was designed to make answers transparent and verifiable. I implemented: 🔹 Vector search for semantic legal retrieval 🔹 Reranking to improve relevance 🔹 Metadata-based source traceability 🔹 Citation-backed answer generation 🔹 Article-level legal references 🔹 Typesense-based retrieval for French judicial cases 🔹 Supporting case law returned with legal answers This allowed lawyers to verify the exact legal source behind each generated response. Open-Source LLM & Cloud Deployment I evaluated and deployed open-source LLM infrastructure for private legal AI usage. The deployment included: 🔹 Qwen2.5:14B for French legal reasoning 🔹 Ollama and vLLM for model serving 🔹 Embedding and reranker models on a private Azure GPU VM 🔹 NVIDIA T4 16GB GPU optimization 🔹 Python/FastAPI backend APIs 🔹 Secure Azure deployment in the France region 🔹 Multi-tenant isolated access 🔹 GitHub CI/CD and Linux server management The system was designed for privacy, reliability, and regulatory compliance. Technologies Used 🔹 Python 🔹 FastAPI 🔹 LangChain 🔹 LangGraph 🔹 LangSmith 🔹 Ollama 🔹 vLLM 🔹 Qwen2.5:14B 🔹 ChromaDB 🔹 Typesense 🔹 Vector Databases 🔹 Reranking Models 🔹 Embedding Models 🔹 Azure Cloud 🔹 Linux 🔹 GitHub CI/CD Impact 🔹 Built a production-ready legal AI assistant for lawyers 🔹 Improved retrieval accuracy from ~50% to 95%+ in tested scenarios 🔹 Reduced hallucinations through citation-grounded generation 🔹 Enabled lawyers to verify answers using article and case references 🔹 Created a scalable legal data pipeline for thousands of documents 🔹 Deployed private open-source LLM infrastructure for legal compliance 🔹 Delivered a strong foundation for future legal AI workflows
0
57
Cover image for [4:07 PM, 7/6/2026] Abdullah: AI
[4:07 PM, 7/6/2026] Abdullah: AI agent that handles scheduling end-to-end 🤖📅 [4:07 PM, 7/6/2026] Abdullah: • Hold context-aware conversations (with memory across the session) • Check your Google Calendar availability • Book new appointments directly • Send confirmation emails via Gmail • Log every interaction to Google Sheets for tracking [4:08 PM, 7/6/2026] Abdullah: No manual back-and-forth. No double bookings. Just a conversational front door that turns “can we find time to talk?” into a booked, confirmed, logged event — automatically. This is the kind of workflow I build for real estate and home services businesses who are tired of losing leads to slow follow-up. If you’re exploring how AI automation could save your team hours every week, let’s talk.
1
55
Cover image for Voice-to-Voice AI Receptionist Assistant for
Voice-to-Voice AI Receptionist Assistant for Businesses My role. AI Agent (Voice-to-Voice AI bot Developer) Project description. Stella AI app, which is a voice-to-voice solution for businesses to manage orders, reservations, and FAQs. I walked through the app's features, including SMS marketing, 24/7 availability, and the ability to customize greeting messages and voice selections. We also explored how to set up a business profile and input a knowledge base and menu through JSON uploads. I demonstrated a live call interaction with Stella AI, showcasing its capabilities in booking appointments. I would love to hear your thoughts on the system and any feedback you might have! Skills and deliverables AI Agent Development AI Bot Artificial Intelligence Natural Language Processing Python
0
68