Technology & AI

My Second Brain Setup That Actually Compounds (Obsidian Edition)

Why Obsidian beats every SaaS note app — and the exact configuration that makes it feel inevitable.

Mar 21 • Atharva Shah

Your New PC Migration Should Not Cost You a Full Day

One PowerShell script installs everything. Another restores every config. Fresh machine in under an hour.

Mar 21 • Atharva Shah

You Don't Need 12 Apps to Dominate Anything. You Need Three.

Obsidian owns your ideas, Wispr Flow speaks them, Copilot transforms them. The full workflow.

Mar 21 • Atharva Shah

Token Anxiety and the Illusion of Productivity

You're leaving parties early to check on agents. You're lying in bed thinking about what you can spin up. We need to talk.

Mar 21 • Atharva Shah

One Command to Share Your Entire VS Code Setup

Every extension becomes a portable install script your team can run in under a minute.

Mar 20 • Atharva Shah

The 30-Minute Copilot Setup That Changes Everything

How agents, skills, and instructions layer together — and why the difference is categorical, not incremental.

Mar 20 • Atharva Shah

The 5 Files That Give Claude Code Permanent Memory

Most developers build one layer of memory. Here are the other four that actually compound

Mar 20 • Atharva Shah

Building AI Marketing Teams with Claude Skills

How to Encode Your Marketing SOPs into Claude with Skill Files & MCPs (A Dummy's Guide)

Mar 19 • Atharva Shah

AI Slop Is YOUR Skill Issue, Stop Blaming the LLMs (+30 Skill Up Scenarios)

Bad Inputs Made Bad Outputs Long Before AI, Here's Your Guide on How to Embrace AI and Dominate Your Field

Mar 19 • Atharva Shah

Practical AI Cost Reduction, Part 3: Advanced Algorithms and Governance

Speculative decoding, activation probes, batching, and taming autonomous agents

Mar 19 • Atharva Shah

Practical AI Cost Reduction, Part 2: Context Optimization and Memory

Caching, compression, and RAG chunking strategies that eliminate token waste

Mar 19 • Atharva Shah

Practical AI Cost Reduction, Part 1: The Tactical Stack

How model routing and tier selection can cut your inference spend by 20–100x

Mar 19 • Atharva Shah

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts