
Why agentic AI breaks the eyeball test, and the eval stack (RAGAS, Promptfoo, Langfuse) that catches what a quick skim misses.
Technical Founder & AI Product Leader | Real AI, real numbers, no leaderboard hype
Product-focused technical founder and AI product leader with 9+ years building software that moves real business numbers — ₹96 crore in cost savings, 95% faster processes, and AI products shipped across legal-tech, fintech, and government infrastructure. I write about AI product decisions with the actual flow behind them, not just the model card.
Markdown supported · ⌘↵ to post
No responses yet.