Blog
What the Top 1% of Developers Build With Claude Code Dynamic Workflows
Multi-agent orchestration is here. HoneyBook collapsed 10 Jira round-trips to one. incident.io runs 4-7 concurrent agents. Anthropic engineers no longer write code. Here is what they are all doing.
Claude Code Routines: A Deep Dive
Claude Code Routines let you chain tool calls into reusable agentic workflows. Here is how the desktop redesign, multi-session support, and 1-hour prompt caching reshape daily work.
The LLM Wiki Pattern: How to Build a Personal Knowledge Base That Actually Compounds
Andrej Karpathy's LLM Wiki pattern replaces RAG with a persistent, LLM-maintained wiki that gets smarter with every source you add. Here is how it works and why it matters for AI engineers.
The Five Pillars of Agentic Engineering
Agentic engineering is not vibe coding. A Meta Staff Engineer breaks down the five pillars separating real AI-native engineering from hope and guesswork.
Before You Run 10 Claude Agents
Most developers think running more Claude Code agents makes them more productive. The opposite is often true. Here is what you need to understand before you scale.
5 Claude Code Plugins That Actually Changed How I Build
I tested nearly every Claude Code plugin over the past few weeks. These five are the ones that stayed installed, and each one shifted something real about how I work.