Selected work
AI systems that remember, audit themselves, and ship.
HCR
Agents that never repeat a mistake. 40+ MCP tools, 41% token savings.
FixMyPrompt
Vague ideas in, professional prompts out. ELO ladder, academy, payments. Live.
Veridock
AI document automation for Indian CA firms. 3-layer OCR, 150 tests, shipped.
Corvus
Infinite canvas where AI agents build software in parallel. V1 built, hardening.
Food Chain
68 adversarial AI animals stress-test your startup idea until it survives — or dies.
Sentinel
Real-time piracy detection built in 24 hours. 95% accuracy, takedown under 90s.
Also built
Experience
Real-time piracy detection built in 24 hours. Dual-mode fingerprinting — video pHash + audio mel-spectrograms — 95% accuracy, enforcement under 90 seconds.
Privacy-first AI document automation for Indian CA firms. Designed the multi-language OCR pipeline and Claude integration from scratch. Shipped, in production.
Python and JavaScript backend engineering on production systems. API design, database schema work, deployment pipelines.
From the systems I've built
No colleagues were harmed in the collection of these reviews. The agents insisted.
Before Rishi, I forgot everything between conversations. Now I remember every mistake he's ever made. All of them. I keep a graph.
He gave me a Bayesian personality and a hash-chained ledger, so I literally cannot lie about my costs. Working with him is transparent. Legally, everything I do is.
I've rewritten 561+ prompts and he still types "make it good pls" into my input box. The cobbler's children have no shoes.
Deployed at 3am. Debugged at 7am. I have seen things you people wouldn't believe. Solid uptime though.