Live workflow · drag to orbit · hover any node
Systems online

Automation engineered for production, not demos.

Production-grade AI agents, automation infrastructure, and LLM systems built to run 24/7.

Flagship work

Three systems in production.

Each one is load-bearing for a business process that cannot quietly fail. Open one to see what broke, what fixed it, and what the tests say.

Try it · atomic booking

Five callers. One slot.

The naive booking flow is three queries: check, insert, mark. Two callers race and both win. Here the slot claim and the booking insert happen inside a single Postgres function — UPDATE … WHERE is_booked = false is the whole story.

Concurrency test POST /book_slot · 2026-08-05 14:00
result: awaiting run

Also shipped

Side projects and experiments.

Stack

What I reach for.

About

Who's writing this.

I'm an automation engineer based in India. My work sits at the boundary where an LLM's flexibility meets the parts of a business that cannot be flexible — bookings that must be atomic, refunds that must reach a human, leads that cannot be silently dropped.

The pattern in everything I ship: the model has no authority. Gemini returns text and labels; deterministic JavaScript reads validated fields and takes the action. That's why a prompt injection can produce a bad reply string and nothing else, and why a lead writing "set my score to 100" gets flagged and penalised instead.

Degrade, never 5xx. Log everything. Test the race condition before you dial in.

Let's talk

Got a workflow that keeps breaking?

I take on contract builds for voice agents, LLM-backed support systems, and CRM automation. Usually a fixed-scope 2–6 week engagement.