*Anthropic just laid out exactly how the biggest companies are running Claude Code on multi-million line monorepos, decades-old legacy systems, and distributed architectures spanning dozens of repos.

The headline of their guide: the harness matters as much as the model. I*

This link will take you to a page that’s not on LinkedIn

Everybody is building agent skills, but not all skills are created equal. Here are some recent research papers that empirically show best practices to build them.

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!" - HKUDS/OpenHarness

*Google published an entire library of highly sophisticated, end-to-end agent examples.

100% open-source.

• Complete documentation • Source code • Ability to one-click deploy

In the video, I break down one of the coolest examples in this collection.

What I love about the Agent Garden is the...

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

Sharla Boehm, a math teacher, spent her summers coding. She’d go on to build what would eventually evolve into the Internet

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.