DEV Community: Kethan Dosapati

I was sick of bad health apps, so I built my own with Next.js

Kethan Dosapati — Fri, 15 May 2026 01:56:01 +0000

Not going to lie I built this app mostly to scratch my own itch.

Every health tracker I tried had the same problem. Great at one thing, terrible at everything else. Or just ugly. Or both. I wanted food logging, water tracking, workouts, weight trends, sleep, and actual AI insights all under one roof, without it looking like a hospital form.

So I spent the last few months building Arogyamandiram. Here's what I actually learned.

The stack

Next.js 15 with the App Router for the full-stack setup. TypeScript in strict mode non-negotiable when you're dealing with health data and math. MongoDB because a daily log is genuinely document-shaped and fighting a relational schema for every new field felt pointless. Tailwind, NextAuth, Recharts, and GPT 4o-mini for the AI layer.

Nothing exotic. Just tools that fit.

The thing I underestimated

The food catalog. I thought it'd take a weekend. It took way longer not because the code was hard, but because getting nutrition data right is actually hard. I ended up with 150+ foods built-in and a USDA FoodData Central API fallback for everything else. Fuzzy search so typos don't ruin the experience. Auto meal-type detection by time of day.

It sounds like a boring feature. It is the feature.

Security stuff I'm proud of

User API keys (for the AI features) are encrypted with AES-256-GCM before they touch the database. Passwords hashed with bcrypt at 12 salt rounds. All API responses filtered server-side so nothing leaks into the browser network tab. Route guards at both the layout level and the API level.

Not glamorous, but it's the kind of thing you only notice when it's missing.

The AI layer and why I was careful

When you ask for AI insights, only anonymized health metrics go to OpenAI. No name. No email. Nothing that identifies you. Just numbers.

And it won't make stuff up. If you haven't logged enough data to generate a meaningful insight, it tells you that. I think an AI that says "I don't have enough yet" is more trustworthy than one that confidently fills your screen with generic advice.

What I'd do differently

Build the onboarding flow first. I built it near the end and had to retrofit the data model around it annoying but fixable. And I'd write more tests for the AI layer specifically. Prompt consistency is harder to test than regular code and I learned that the slow way.

Try It
Live - https://arogyamandiram.vercel.app
Code - https://github.com/utsaaham/arogyamandiram - MIT licensed, and the setup actually works if you follow the README.
If you find a bug, want to contribute, or just tried it - I'd love to hear from you.

Turning AI Ideas into MVPs in Weeks, Not Months

Kethan Dosapati — Fri, 05 Sep 2025 14:42:50 +0000

Ever had an AI idea you were really excited about…
only to see someone else launch it the very next day?

👉 I’ve been there. That’s why I’m starting my journey as a founder.

I’m building a platform that helps turn AI ideas into real, production-ready MVPs in weeks not months. The goal is simple: make it faster and easier for founders, investors, and builders to bring their vision to life.

⚡ What’s inside the platform

Pre-built AI infrastructure (no need to reinvent the wheel)
Multi-agent orchestration
Real-time streaming chat
Secure, locally hosted LLMs (your data stays safe)
Document Q&A (PDF, DOCX, TXT, HTML)
Web scraping + search integration
Persistent conversation memory ...and more 🚀

🎥 Platform Walkthrough

👉 Watch the walkthrough

🌐 Portfolio

🔗 Don't click me 😉

💬 Let’s Connect

I’d love to connect with other founders, investors, and AI-curious builders.
If you’re working on something in this space—or just want to brainstorm—let’s chat.

Drop a comment or DM me. Always happy to swap ideas.

AI MVP Development Made Simple: Delivered in Weeks

Kethan Dosapati — Tue, 26 Aug 2025 16:29:41 +0000

I’m working on a base AI platform to help founders and devs launch faster—without rebuilding the same boilerplate every time.

What’s inside

Editable landing page – tweak without writing code
Complete authentication system – login, signup, forgot password, JWT + API key security
ChatGPT-style interface – streaming responses, context memory (internal RAG pipelines), chat history, search, file uploads
Extensible AI agents + MCP integration – plug-and-play new agents/tools
Smart left + right sidebars – manage conversations, docs, and recent tool history
API key management – generate and use keys internally (no data leakage)
Document intelligence – upload PDFs, DOCX, TXT, HTML and query contextually
Locally hosted AI models – privacy-first architecture (your data stays with you)

👉 Working demo

Real-world test: Teacher’s AI Assistant

To test the platform, I built a teacher’s AI assistant in just weeks. It can:

Read and answer from uploaded docs
Extract key concepts + break down topics
Create structured study plans
Generate flashcards for quick revision
Build flowcharts from raw ideas
Create quizzes and grade answers
Provide last-minute exam prep with contextual Q&A

👉 Demo here

Tech stack

Backend: FastAPI + MongoDB
Auth: JWT + API Key system
Frontend: React (Material-UI, responsive + dark theme)
Integrations: OpenAI + MCP (Model Context Protocol)
Infra: WebSockets for real-time streaming, locally hosted models

While You’re Still Planning… Your Competitors Are Already Launching

Kethan Dosapati — Fri, 15 Aug 2025 00:25:07 +0000

Every week, I meet founders and investors who are sitting on brilliant ideas. They have the funding. They have the vision. But their product? Still stuck in planning mode.

Meanwhile, competitors are moving fast — launching MVPs, talking to real users, and attracting more funding.

The difference isn’t always the idea. It’s speed to execution.

What We Do

Me and my team specialize in turning ideas into production-ready MVPs in weeks, not months. Our builds are scalable, investor-ready, and tailored to your exact vision.

We Deliver

Generative AI & RAG – Vector search, semantic search, real-time document Q&A, MCP integration
Custom AI Agents – Multi-model (GPT-4o, Claude, Gemini), agentic workflows
Web & Document Intelligence – Scraping, data extraction, insight generation
Scalable SaaS Infrastructure – MongoDB, WebSockets, enterprise-grade security

My Work

Portfolio: https://dkethan.github.io/kethandosapati/
GitHub: https://github.com/DKethan

Let’s Build It

If you’re a startup founder, VC-backed entrepreneur, or investor with an idea that’s ready for execution — let’s talk. We’ll get your product live before your next investor call.

Tags: startups mvp ai generative-ai rag ai-agents venture-capital saas llm machine-learning deep-learning langchain kubernetes docker product-launch founders