milanSathi
milanSathi
Built milanSathi, an in-house AI-powered astrology engine (kundli + kundli-milan) that replaced a paid third-party astrology API.
- ~$45,000/year saved
- 100% parity with the vendor on everything tested
What I do, 1 of 5
If a vendor bill grows with your traffic, I build the in-house version and prove it gives the same answers before you switch.
A small working tool. Change the numbers.
Put in your vendor bill and a rough build cost. See when building pays for itself.
A rough estimate to start the conversation. My two replacements save about $115,000 a year combined.
milanSathi
Built milanSathi, an in-house AI-powered astrology engine (kundli + kundli-milan) that replaced a paid third-party astrology API.
Jeevansathi
Built an in-house feature-configuration platform (Spring Boot, Redis, MongoDB) that replaced Firebase Remote Config after it moved to a paid tier.
milanSathi
Proved correctness against the vendor before switching traffic.
Kundli match
Ashtakoota, 8 kootas
Good match
AI conversation starter
You both have the Moon in earth signs. Ask about the last thing they built with their hands.
Illustration with sample scores
home_screen_variantAndroid"off"a build with a known bug"v2"new home screen"v1"app defaultThe app gets "v2"
Most teams use a fraction of what they pay for. That fraction is all we rebuild.
Same contract, so the rest of your code barely notices.
Check it against the vendor on real data before any traffic moves.
Roll out behind a flag, with automatic fallback to the vendor.
Tell me what you're working with. I'll tell you honestly whether it's worth doing and roughly what it takes.
Email me about thisAnswers only from what's on this site. If it isn't here, it says so.
Hi! Ask me anything about Devatraj's work, skills or background.