AI Development Projects in GujaratAI Development Projects in GujaratBuilt a complete multi-page digital experience using Google Stitch.
For this project, I designed and prototyped Eternal Maven, a modern AI and technology agency website focused on communicating technical expertise, credibility, and premium brand positioning.
What I created:
• Homepage with a bold, future-focused visual identity
• AI Development, Web Development, and Solutions pages
• Case Study section featuring project outcomes and impact metrics
• Industry-specific expertise showcase
• Technology Stack page highlighting modern tools and platforms
• Portfolio gallery for featured work
• Blog & Insights hub for thought leadership content
• Contact and conversion-focused lead generation experience
How I used Google Stitch:
I leveraged Stitch to rapidly generate, refine, and prototype high-fidelity screens while maintaining a consistent design system across the entire experience. The platform made it easy to explore ideas, iterate quickly, and build a cohesive multi-page user journey.
Design Direction:
Dark immersive UI, electric blue accents, glassmorphic elements, modern typography, and premium visual storytelling designed for a 2026-ready digital presence.
Prototype: https://stitch.withgoogle.com/preview/10522833652304720789?node-id=98d3602ef68e4bcb88b235a2ac03a4d0
#GoogleStitch #WebDesign #UIDesign #UXDesign #AI #ProductDesign #Prototype #DigitalExperience #Contra OneBrain AI — One App. Every AI. Limitless Creation.
Overview
OneBrain AI is an all-in-one multimodal AI assistant that brings conversational AI, image generation, video creation, audio tools, and voice capabilities into a single streamlined mobile experience. Instead of switching between multiple AI platforms and creative tools, users can access leading models including ChatGPT and Gemini, generate multimedia content, automate everyday tasks, and interact with AI from one unified interface.
Built for productivity, creativity, learning, and everyday assistance, OneBrain AI combines powerful generative AI capabilities with an easy-to-use mobile experience, multilingual support, and privacy-focused data handling.
Key Features
Multi-Model AI Chat — Access leading conversational AI models including ChatGPT and Gemini from one unified application.
AI Image Generation — Create high-quality AI-generated visuals using advanced image-generation models through dedicated creation workflows.
AI Video Generation — Turn ideas and prompts into AI-generated videos, including support for advanced video-generation technology such as Google Veo.
Voice & Audio AI — Use voice input and AI-powered audio capabilities for more natural, hands-free interaction and multimedia creation.
Agentic AI Assistance — Go beyond basic chatbot interactions with AI assistance designed to help complete tasks, generate content, and streamline workflows.
Unified Multimodal Workspace — Chat, generate images, create videos, work with audio, and use voice tools without jumping between separate AI applications.
Task & Workflow Automation — Use AI to accelerate repetitive tasks, content workflows, research, ideation, and day-to-day productivity.
Multilingual Experience — Communicate with AI across multiple languages for broader accessibility and global use cases.
Privacy & Security — Designed with encrypted data transmission, user privacy controls, and compliance readiness as part of the platform experience.
Product Experience
OneBrain AI is designed around a lightweight, mobile-first interface that makes advanced generative AI accessible without requiring users to understand or manage multiple standalone tools. The experience brings conversational and creative AI into one ecosystem, allowing users to move naturally between asking questions, generating content, creating visuals, producing videos, and working with voice or audio.
Results
Shipped as a production Android application with 5,000+ Google Play downloads, bringing conversational AI and multimodal generation into one unified mobile product. OneBrain AI gives users a single destination for ChatGPT, Gemini, image generation, AI video, audio and voice tools, agentic assistance, and workflow automation while maintaining a strong focus on usability and privacy. B2B Travel Tech & Fintech Platform
Its is the enterprise B2B division built to give major airlines, banks, and travel brands access to Hopper's advanced booking technology, AI pricing models, and travel fintech products under their own brand.
The client needed a scalable, high-performance web platform that clearly communicates complex enterprise offerings — travel fintech ancillaries, white-label loyalty portals, cross-selling e-commerce tools, and agentic AI customer service — to a sophisticated B2B audience including partners like Capital One, Air Canada, and RBC.
We developed a fast, modern Next.js web platform with a clean enterprise UI, optimized for performance and designed to convert high-value corporate visitors into technology partners.
The result is a polished, conversion-focused platform that positions it as a credible infrastructure partner for the world's largest travel and financial brands. I designed and built Pristine's entire digital operations platform, from database architecture and role-based workflows to a production-deployed web suite and an AI analytics layer.
The challenge was replacing a ceramic processing plant's paper-and-spreadsheet production logs with a system that floor operators would actually use, while giving management the traceability and insight the paper trail never could. Every decision focused on data integrity, least-privilege security, and keeping the interface simple enough for shift operators to work quickly.
I built four services around a single PostgreSQL schema. The operator app handles the full production lifecycle: raw material intake, drying plant shifts, multi-section ball mill batch entry, quality control, and finished-goods inventory, with Excel export throughout and navigation that adapts to each of eight distinct plant roles. A modular Express and Prisma API enforces that access control at the route level. A separate React-Admin console keeps master data (mills, grades, recipes, suppliers, users) out of the operator's way.
The most important piece was traceability. I designed a quality control gate that sits between production output and inventory. QC records are created automatically when a batch completes, reviewed by an inspector, and only generate an inventory entry if quality passes. Every finished bag carries an auto-derived lot number encoding its production date, flow rate, monthly sequence, and bag count, so any outbound shipment can be traced back through inventory and QC to the exact mill batch that produced it.
On top of that I built an AI analytics agent that lets managers query the plant in plain English, architected around a zero-data-to-LLM guarantee. The model only ever sees the database schema and the question, never a row of production data. Five independent layers enforce it: two least-privilege Postgres roles separating read-only queries from insert-only auditing, a sqlglot AST guard that rejects any non-SELECT statement, a per-role table allowlist, the prompt design itself, and a full audit log of every interaction. Answers stream to the browser over Server-Sent Events through a LangGraph pipeline that routes, guards, plans the query, executes, then explains the result in business terms.
Tech Stack: React 19, TypeScript, Ant Design, TanStack Query, Tailwind CSS v4, Node.js, Express, Prisma, PostgreSQL, React-Admin, MUI, Python 3.12, FastAPI, LangGraph, OpenAI, AWS EC2, Nginx, Supabase, Vercel. 
