Harshavardhan

My Writing

Notes on building AI products — LLM systems, real-time architecture, and the things that actually break in production.

2026-05-0810 min read

My First Month at Mynaksh: Two Things Nobody Asked Me to Fix

I joined as a senior engineer. In my first month I rewrote the data layer and built a versioned deploy system. Neither was on my JD. Here's why I did them anyway.

React NativeTanStackDevOps

2026-05-058 min read

An AI On-Call Engineer: Multi-Phase Triage with Grafana and GitHub MCPs

When a microservice goes down at 3am, the slow part isn't fixing it — it's figuring out which service is actually broken. We built an LLM agent that does the triage.

AgentsMCPOn-CallObservability

2026-05-027 min read

Wallet Reservations at the Redis Layer: How We Stopped Double-Billing Users

When users pay per minute for a call, the wallet is on the critical path. Here's how we used Redis-level reservations and locks to prevent double-billing and negative balances.

RedisDistributed SystemsPayments

2026-04-308 min read

Building an AI Astrologer: Personas, Rolling Summaries, and Tone-Matched Replies

An LLM that does astrology readings sounds like a gimmick. Building one that feels like a different astrologer for every user is a real engineering problem.

LLMPersonalizationProduct

2026-04-229 min read

Building a Real-Time Calls Feature on CometChat: What Actually Hurts

Two React Native apps, one CometChat SDK, and a long list of edge cases. Here's what we learned shipping live consultations between users and astrologers.

Real-TimeReact NativeCometChat

2026-04-157 min read

Healthcare AI to Consumer AI: What Changes When the Stakes Drop

Six weeks ago I was building systems where a 2% error rate meant 2,400 patients got denied care. Today I'm building astrology consultations. Here's what that switch actually feels like.

CareerAIConsumer Tech

2025-03-018 min read

Building Healthcare AI at Scale: Lessons from the Trenches

The messy, complex, and rewarding reality of building AI systems that process 120k+ medical procedures daily.

AI/MLHealthcareEngineering

2025-02-016 min read

From Startup Founder to Healthcare AI Engineer: My Journey

How I transitioned from building a freelancing platform to revolutionizing healthcare automation with LLM technologies.

CareerEntrepreneurshipAI

2025-01-0112 min read

LLM Evaluation in Production: How We Hit 98% Accuracy

A deep dive into the code and concepts behind our 98% accurate medical data extraction pipeline.

LLMsEvaluationHealthcare Tech

2024-12-0110 min read

Serverless Architecture: The Hard Lessons

Everyone told us not to use serverless for a production startup. We did it anyway. Here is what broke, and how we fixed it.

AWSServerlessArchitecture