AskMyAstro
An AI astrologer that reads your birth chart and answers real questions over chat — LLM prompt pipeline, chart computation and the full product around it, built and operated solo.
1.1K+ users · 4.7K views
open to opportunities · Gurgaon, India
Sarthak Chhabra
Technical Lead — I architect the platforms that put AI agents into production: routing engines, RAG pipelines and no-code tooling that turn weeks of engineering into minutes of configuration.
$ agent run whoami --stream
44Mtokens/day
300K+LLM req/day
15–20msrouting latency
7+years shipping
01 · proof of work
Numbers from production, not slides.
Every metric below is live or was measured in a shipped system. This is what my work does when real users hit it.
stashfin · production
0M
LLM tokens processed every day by the customer-support agent I architected — ~30,000 messages across 6,000+ daily users.
zupee · llm router
0K+
Requests/day through a centralized LLM routing engine — 15–20ms latency, 99% uptime, multi-provider fallbacks & circuit breakers.
retention
0%
D15 retention on an AI companion chatbot — LangGraph multi-agent planning + RAG memory.
velocity
0×
Faster content production — promo generation cut from one week to 3 hours.
delivery
days → minutes
Agent delivery time after the no-code platform — prompt, tools, model & channel, all self-serve.
02 · live products
Built solo. Running right now.
Side products I design, ship and operate myself — with real traffic and live numbers straight from analytics.
FileDownloader
A bulk file-download utility serving real traffic on the open internet — paste URLs, get files. Simple tool, sticky usage: over half a million downloads served and counting.
544K+ downloads · 5.9K+ users
03 · systems
Things I've architected.
Platforms and infrastructure designed so that other people — engineers and non-engineers alike — can ship intelligence.
No-Code AI Agent Platform
A self-serve platform for building and deploying production AI agents — configure prompt, tools, model and channels from a UI, ship in minutes. Runs multiple production agents today, including a support agent serving 6,000+ users daily.
agent delivery: days → minutes · 44M tokens/day in production
Centralized LLM Routing Engine
One gateway for every LLM call in the company — budget tracking, rate limiting, multi-provider fallbacks and circuit breakers so product teams never think about provider outages.
300K+ req/day · 15–20ms · 99% uptime
AI Companion Chatbot
LangGraph multi-agent architecture for response planning and conflict resolution, RAG memory on Qdrant, and human-like dynamic response timing.
46% D15 retention
Dynamic Tool Framework
Turns any REST API into an agent-callable tool: configure the request, fire a live test call to capture the real response shape, annotate keys — the LLM tool schema writes itself. Zero hand-written integrations.
any API → agent tool, no code
RAG Ingestion Pipeline + Cross-Channel Memory
End-to-end knowledge pipeline — upload, chunk, embed, store — plus a contact system that unifies a user's email, phone and Slack identities into one persistent memory, so agents never start cold across channels.
custom knowledge bases, zero engineering support
Automated Promo Generation
Parallel processing of 50–100 microseries for ad creative — accelerating A/B testing cycles and campaign deployment, with a no-code bot management console for product managers on top.
1 week → 3 hours production time
04 · timeline
Seven years, six chapters.
FEB 2026 — JUL 2026
Technical Lead · Stashfin
NodeJS · TypeScript · AWS · Postgres · GenAI · Docker · Microservices
- Architected a no-code AI agent platform — agent delivery cut from days to minutes; runs production agents handling ~30K messages & 44M tokens/day.
- Built a dynamic tool framework turning any REST API into an agent tool via live schema capture.
- Unified cross-channel user identity with persistent agent memory across email, phone & Slack.
JUL 2025 — FEB 2026
Technical Lead · Zupee
NodeJS · Postgres · Qdrant · MongoDB · LangGraph · GenAI
- Built the centralized LLM routing engine: 300K+ req/day, 15–20ms, 99% uptime.
- Shipped an AI companion with 46% D15 retention; led a team of 4 across multiple AI products.
- Cut promo production from one week to 3 hours with automated generation.
MAR 2022 — APR 2025
Senior Software Engineer · Dresma AI
NodeJS · TypeScript · AWS · MongoDB · Kafka · Microservices
- Cut response times 40% and lifted system efficiency 30% across heavy-computation services.
- Designed near-fail-proof architectures: +50% stability, −30% processing time.
- Mentored junior engineers — +20% delivery efficiency, −30% error rates.
MAY 2021 — MAR 2022
Full Stack Developer · Gigforce
NodeJS · AWS SQS · MongoDB · VueJS
- Owned modules end-to-end: +25% stability, −40% peak-load latency, −30% query response time.
OCT 2020 — MAY 2021
Software Developer · Signcatch
ReactJS · Angular · SQL · PHP
- Shipped across the full SDLC — −20% time-to-market, −15% churn.
JAN 2019 — OCT 2020
Associate Software Engineer · Bosch
Angular · C# · SQL
- Cross-platform applications with rigorous version control — −25% ticket resolution time.
AUG 2015 — JUL 2019
B.E. Computer Science · Lovely Professional University
8.7 CGPA
05 · stack
Tools I think in.
AI / LLM Systems
Backend Engineering
Infrastructure
Leadership & Product
06 · about
The human behind the systems.
I'm Sarthak — a Technical Lead based in Gurgaon, India. My career has one through-line: removing the engineering bottleneck between an idea and a running system.
At Bosch I learned discipline. At startups I learned speed. At Dresma I learned to build things that don't fall over. And in the AI era, I've found the work I love most: platforms that let non-engineers deploy production-grade AI agents — routing engines that survive provider outages, RAG pipelines anyone can feed, tool frameworks that turn any API into an agent capability.
I lead small teams, I stay close to the code, and I measure my work in production numbers — not promises.
07 · contact
Let's build something
intelligent.
Whether it's AI infrastructure, agent platforms, or a hard scaling problem — my inbox is open.