Moiz Ahmed Mansoori
AI Assistants, RAG Chatbots & Business Workflow Automation
New to Contra
Moiz Ahmed is ready for their next project!
Most people think generating a 3D model is the hard part.
It isn't.
The real challenge is generating something that's actually usable.
That's why I built VoxelVia3D.
Instead of producing random meshes, it turns a simple text prompt into a structured 3D asset that creators can immediately preview and download.
What I focused on wasn't just AI generation.
It was the complete product experience:
• Clean web interface
• Fast AI inference
• Real-time generation progress
• Downloadable 3D assets
• Responsive, production-ready deployment
The difference between a cool AI demo and a useful AI product isn't the model.
It's everything around the model.
That's the kind of AI software I enjoy building.
🌐 voxelvia3d.app
(http://voxelvia3d.app)💼 contra.com/moiz_roshan_zszcum4s
2
95
I built an AI wellness app that does more than generate responses.
It listens, remembers context, and responds with emotional guardrails in place. https://asksukoon.com/
Most “AI wellness” tools today are just chat interfaces with a mental health label attached.
AskSukoon was built differently.
What’s inside:
— Voice conversations with sentiment-aware responses
— Memory-powered support using ChromaDB
— Guardrails for sensitive interactions
— Guided reflections and mood tracking
— Fast, mobile-friendly experience built for real users
The hardest part wasn’t connecting an LLM.
It was designing something that feels calm, safe, and usable in production.
Shipping this taught me more about product than 3 years of coursework
Live: https://asksukoon.com/
Services: contra.com/moiz_roshan_zszcum4s
1
170
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
1
181
Built AIRO, a 6-agent ML automation system using LangGraph and Groq LLaMA 3.3. The system automates the entire ML pipeline from data ingestion to final report generation. Ran 18 experiments achieving RandomForest f1_macro of 0.7329. Features parallel training, MLflow tracking, SHAP explainability, and a dark Streamlit UI with live log streaming.
2
266