hi i'm prasad
i do AI and crypto stuff.
Blog
how LoRA actually scales
May 2026The math and GPU trick behind serving thousands of LoRA adapters from a single base model — without ever merging weights.
why most agents are poorly built
Apr 2026Most teams are shipping agents that feel like glorified chatbots - here's what's going wrong and how to actually fix it
efficient tool selection with SLMs
Mar 2026How I optimized tool selection for on-device agentic AI — from ~3 seconds to ~15ms using weighted embeddings
i built private vector search
Feb 2026Building encrypted vector search with homomorphic encryption — from 6.5s to 172ms with 95% recall
the control plane for llm inference
Jan 2026Building an event-driven LLM inference architecture
how I manage stacked branches
Jan 2026Learn how to effectively manage stacked branches in Git for cleaner code reviews and faster iteration cycles.