Blog
Claude Code in Production: What Senior Engineers Actually Need to Know
Most teams using Claude Code are running it at 20% of its actual capability. Here is what teams actually getting leverage are doing differently — from CLAUDE.md to multi-agent file coordination.
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.
Six Agent Frameworks in One Week: The Tooling Is Free, the Architecture Bill Comes Later
Hermes, DeerFlow, Nanobot, and three more agent frameworks shipped in a single week. The real challenge is not picking one. It is orchestrating them without context rot destroying your production outputs.
UltraPlan in Claude Code: Cloud Planning With Multi-Agent Architecture
UltraPlan moves Claude Code planning to the cloud with 3 parallel explorer agents and a critic. Here is what it actually does and where it falls short.
Inside OpenAI's Dark Factory: 1M Lines of Code, Zero Human Authorship
Ryan Lopopolo's team at OpenAI shipped 1 million lines of production code with zero human-written source. Here is what their Symphony system, ghost libraries, and post-merge review workflow actually look like.
Scion: Google Cloud's Open Source Hypervisor for AI Agents
Google just open-sourced a multi-agent orchestration testbed that runs Claude Code, Gemini CLI, and Codex in isolated containers. Here is how Scion works and why bounded agency matters more than model capability.
Your Agent Moat Was Never the Orchestrator
GitHub just turned the agent harness into a commodity. Here is why that is good news for enterprises, and bad news for anyone who spent 2025 building a proprietary framework.
OpenAI's Harness Engineering Explained
Harness Engineering is how OpenAI shipped 1 million lines of production code in 5 months with 7 engineers and no manually written source code.
Building a Long-Running AI Agent Harness
Every new Claude Code session starts with no memory of the last. Anthropic's engineering team built a two-part harness that fixes this. Here is what it does and how to implement it.
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.