Shipped this weekend: a 3-agent blind cross-lab evaluation workflow on heym, MIT licensed, callable...
I open-sourced a 3-agent blind eval team. Any agent runtime can call it for pre-commitment review of its own plans.
Related
Interim Log: My First Real Mobile Coding Session – Voice, AI Connectors & The Current State of Developer Tooling
Disclaimer / Introduction This interim log post was drafted in collaboration with Grok 4 (xAI). I...
The Agent Is 20% of the Work. The Platform Is the Other 80%.
A payroll agent hit 94% accuracy in testing and dropped to 70% in production. What closed the gap had nothing to do with the model. Here's what that means for every enterprise team...
I Stayed Up Until 3 AM to Build a Better Claude Code Guide Than the One With 52,000 Stars — Here's What I Found
One night. One obsession. One repo that changed how I think about AI-assisted...