Kimi-K3 solved 94% of workflows once. Only 13% survived every run
New evidence separates occasional agent capability from dependable operation, while applied teams show where task choice, model training, and runtime retrieval each belong.
Topic · 2 articles
Context Engineering
The latest analysis on Context Engineering, across Daily Pulses and Weekly Reviews.
October 2026
September 2026
The agent harness is becoming a managed runtime, and policy is moving into the control plane
OpenAI externalizes the Codex harness as a managed Agents API, Anthropic adds server-evaluated tool permissions, and new military-domain evaluations show why runtime controls matter below the absolute model frontier.