惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

C
Check Point Blog
aimingoo的专栏
aimingoo的专栏
Jina AI
Jina AI
Microsoft Security Blog
Microsoft Security Blog
IT之家
IT之家
V
Visual Studio Blog
量子位
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - 聂微东
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
大猫的无限游戏
大猫的无限游戏
Y
Y Combinator Blog
Stack Overflow Blog
Stack Overflow Blog
D
Docker
MyScale Blog
MyScale Blog
小众软件
小众软件
云风的 BLOG
云风的 BLOG
美团技术团队
Microsoft Azure Blog
Microsoft Azure Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
Last Week in AI
Last Week in AI
Apple Machine Learning Research
Apple Machine Learning Research
博客园 - 【当耐特】

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
I Built an AI Assistant for Bangladesh — Introducing RexiO
Mohammad Sijan · 2026-05-31 · via DEV Community

Mohammad Sijan

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.