The blog.
17 posts on automation, page 1 of 2RSS feed
How to Build an Agentic OS (Claude OS) That Actually Works
An Agentic OS isn't about fancy dashboards. It's a three-layer system — skills, memory, and visual — that routes your work across GPT-6, Claude Opus 5.5, and Jev so AI actually takes work off your plate.
10 Claude Code Concepts That Actually Matter
The 10 Claude Code concepts that actually move the needle — from picking the right model and effort level to loop engineering and dynamic workflows.
Graph Engineering vs Loop Engineering: What Changed
Graph engineering is loop engineering split across multiple connected agents, each running its own loop with its own success criteria. Here are the three scenarios where it is worth the complexity.
Loop Engineering: The 4-Phase Process (and Why Prompt Engineering Isn't Dead)
Loop engineering is just prompts stacked on prompts and repeated until a success criteria is met. Here's the 4-phase anatomy, the 4-step maturity path, and the one decision that determines whether your loop works.
How to Build a Voice-Driven Agentic OS on Claude Code
Jarvis is a local, voice-driven Agentic OS built on Claude Code — Faster Whisper for speech, Haiku for routing, headless Claude Code for the work, and Kokoro for the voice. Here's how the whole thing runs and how to build your own.
The Agentic OS Mistake: You're Building the Dashboard First
Most Claude Code agentic OS builds chase flashy dashboards and miss the only layer that actually drives value: the skill and automation backbone. Here's the order that actually works.
How the Higgsfield MCP Server Turns Claude Code Into a Content Machine
The Higgsfield MCP server gives Claude Code one connection to every major AI image and video model. Here's the install and the exact workflow I used to hit 100K views.
How to Build a Claude Code Agentic OS (Memory, Skills, Dashboard)
A Claude Code agentic OS closes the memory, consistency, and access gaps. Here is the full architecture and the order to build it in.
Claude Code /routines: How Scheduled Cloud Tasks Actually Work
Anthropic just shipped /routines for Claude Code — scheduled, API, and event-driven tasks that run in the cloud. Here's what works and what the limits are.
OpenClaw Is Overhyped: What Nobody Tells You
OpenClaw is a great tool — but it's not great for the reasons AI influencers are telling you. Here's the honest breakdown of its real value, its real costs, and why most of its hyped use cases are productivity theater.
How to Convert n8n Workflows to Python Apps (Using Claude Code)
n8n is great for prototypes, but production apps need real code. Here is the exact framework for converting n8n JSON files into full Python applications using Claude Code.
OpenClaw Setup Guide: How to Connect Google Workspace Securely
OpenClaw is the fastest-growing open-source AI project, but connecting it to Google is a nightmare. Here is the step-by-step guide to hosting it on a VPS and navigating the complex authentication process.
