Hi, I'm Sanath

I'm a software engineer specializing in scalable backend systems and AI-powered products. I've helped companies grow platforms to millions of users, working with TypeScript, Python, Rust, and AWS.

Currently focused on generative AI and agentic systems. This site shares my writings on software engineering, backend architecture, and AI development.

Featured

• The Three Layers Every Production RAG System Needs

  Updated: 16 Feb, 2026

  Document parsing, hybrid search, and orchestration - the three layers that separate toy RAG demos from production systems.

• The 5 MCP Servers Every Developer Needs in 2025

  Updated: 1 Feb, 2026

  The 5 MCP servers that actually matter for your AI-powered dev workflow - semantic code nav, GitHub automation, browser testing, live docs, and persistent memory.

• AI Won't Replace You - But a Developer Using AI Will

  31 Jan, 2025

  Why your experience as a software engineer matters more than ever in the AI era, and how to actually get good at working with AI agents

• How to make eslint and fixers blazingly fast in neovim

  20 Jan, 2024

  A guide to setting up ALE with eslint_d for lightning-fast linting in Neovim

Recent Posts

• The Simple Loop Behind Every Fancy Agent

  9 Mar, 2026

  Every sophisticated agent harness still boils down to this tiny loop: call the model, run tools, feed results, repeat.

• Building AI Agents at Home with OpenClaw (Without Losing Your Mind)

  25 Feb, 2026

  A practical guide to running useful AI agents from your own machine with OpenClaw, including architecture, memory, workflows, and lessons learned.

• How OpenClaw Gives AI Agents Persistent Memory With Plain Markdown

  1 Feb, 2026

  A deep dive into how OpenClaw's file-based memory system gives AI assistants genuine continuity between sessions using Markdown files, semantic search, and automatic memory flush.