Phil SchmidVoices
Evaluating Agents Beyond the First Prompt
EvoCode-Bench tests coding agents across 227 sequential rounds in a persistent workspace. Single-turn scores overstate reliability — regressions, not missing features, are the real bottleneck.
Read at Phil Schmid ↗Related
VoicesPractical Guide to Evaluating and Testing Agent Skills Phil Schmid

ResearchCapturing token IDs during agentic interactions for better reinforcement learning Amazon Science

LanguagesModular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More Mojo Blog

VoicesEvals Skills for Coding Agents Hamel Husain
