Skip to content

Posts

All the articles I've posted.

Jul 13, 2026

Personal Agentic OS: who will own the personal knowledge layer?

Frontier models are converging into commodities; your accumulated context is the one input nobody else has. The personal knowledge stack now exists — format, capture, sync, protocol — except for the one layer nobody has an incentive to standardize: governance. It's the last moat left, and whoever owns it owns the model of you.

Read →
Apr 24, 2026

After the Browser

the agent harness is the new browser, MCP is the new HTTP, and the hard problems have moved from the loop to the tool layer, context management, and federated capability.

Read →
Apr 4, 2026

The claw-code Story: What's the Harness?

The architecture behind the most important leak of AI history, and probably the inflexion point for agent orchestration

Read →
Apr 4, 2026

From Conductor to Orchestrator: A Practical Guide to Multi-Agent Coding in 2026

The complete landscape of multi-agent coding orchestration — from Claude Code Agent Teams to Oh My OpenAgent, the Ralph Loop pattern, and how to choose the right tier for your workflow

Read →
Apr 4, 2026

From Conductor to Orchestrator: A Practical Guide to Multi-Agent Coding in 2026

The complete landscape of multi-agent coding orchestration — from Claude Code Agent Teams to Oh My OpenAgent, the Ralph Loop pattern, and how to choose the right tier for your workflow

Read →
Apr 3, 2026

Pi AI SDK vs Anthropic Claude Agent SDK

"The analogy from the ecosystem that resonated most: Claude Code is "Rails" — opinionated, structured, with best practices baked in. Pi is "Arch Linux" — giving you the smallest kernel and the greatest freedom. "

Read →
Mar 28, 2026

What Is OpenClaw and How It Can Help You Be More Efficient

A practical guide to OpenClaw — the open-source AI agent framework that connects LLMs to your operating system, messaging apps, and tools. Understand its architecture and how it can automate your workflow.

Read →
Mar 28, 2026

What Is Claude Cowork and How It Can Help You Get More Done

A practical guide to Claude Cowork — Anthropic's desktop AI agent for knowledge workers. Learn how it automates document processing, file management, and multi-step workflows without writing a single line of code.

Read →
Mar 28, 2026

Why 90% of AI agent tools are useless (and 7 that aren’t)

An updated analysis of 7 open-source platforms redefining AI implementation in 2026: Activepieces, Dify, Langflow, n8n, Flowise, Botpress, and CrewAI — covering agentic workflows, MCP adoption, and human-in-the-loop capabilities

Read →
Mar 28, 2026

Building Your AI Agent Skills Library: A Practical Guide for Data Engineering Teams

Building Your AI Agent Skills Library: A Practical Guide for Data Engineering Teams How to collect, organize, document, and deploy specialized knowledge for Claude and other AI coding agents The …

Read →