DEV Community

Mohammad Sijan
Mohammad Sijan

Posted on

I Built an AI Assistant for Bangladesh — Introducing RexiO

Most AI assistants are built for English speakers. I wanted to change that.

RexiO is a premium AI assistant built specifically for Gen Z users in Bangladesh. It understands Bengali and Banglish naturally, searches the web in real-time, and builds a personal knowledge panel for every user — all in a fast, modern interface.

What RexiO Can Do

  • Real-time Web Search — RexiO searches the web live and summarizes results directly in the chat
  • Personal Knowledge Panel — RexiO builds a persistent knowledge base for each user, learning preferences and context over time to deliver increasingly personalized responses
  • Voice Chat — Full real-time voice interaction
  • Live Weather — Ask about weather anywhere and get instant results
  • Image Search — Ask for images and RexiO finds and displays them inline
  • Cross-platform — Available on Android (native app) and as a PWA for desktop and iOS
  • Scheduled Tasks (Coming Soon) — Automate recurring tasks and set scheduled prompts directly inside the chat

The Challenge

Building an AI assistant for Bangladeshi users is not just a translation problem. Users naturally mix Bengali and English in the same sentence — called Banglish. The system has to understand intent, not just language. That required building a custom multi-tier intent classification pipeline from scratch.

On top of that, the backend had to handle real-time streaming responses, live web search, personalized memory, and voice — all simultaneously, reliably, on production-grade infrastructure.

Architecture Decisions

The backend is built as a microservice architecture with three isolated services — each chosen for what it does best.

The public gateway prioritizes zero-latency streaming with no buffering on SSE connections. The core engine handles all stateful business logic, real-time sessions, authentication, and payments. The AI layer runs as a completely isolated service for agent workflows, web scraping, intent classification, and multi-agent coordination.

This separation means each layer can be scaled, updated, or replaced independently without touching the others.

The personal knowledge panel runs as an asynchronous background system — it learns from every conversation without adding any latency to the main chat response.

What's Next

RexiO is currently in development and launching soon. The goal is simple — make cutting-edge AI feel native for millions of Bangla-speaking users who deserve better than a translated chatbot.

Check it out at rexio.pro.bd


Built by SpritEX — a Bangladesh-based AI company.

Top comments (0)