/ esc
sanath @ dev : ~/writing $ ls -la | grep "*"

writing

Notes from shipping things. Mostly backend, AI agents, developer tooling, and the occasional rant about CSS.

/ 6 of 6
Every sophisticated agent harness still boils down to this tiny loop: call the model, run tools, feed results, repeat.
Document parsing, hybrid search, and orchestration - the three layers that separate toy RAG demos from production systems.
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.
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.
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
A guide to setting up ALE with eslint_d for lightning-fast linting in Neovim