Refuse Over Guess
Essay · September 2, 2026 · 12 min read
Why the most important design decision in a production AI system is deciding when the model is not allowed to answer, and how to engineer that refusal.
Tagged: agentic-ai
5 items · All tags
Kimi K3: The Architecture Was Decided By The Kernel
July 30, 2026 · 6 min read
Reading the Kimi K3 technical report from the seat of someone who builds agentic systems that have to run on Monday morning: the decisions were made by kernels, caches, and harnesses, not loss curves.
Skills, Connectors, and Subagents: Decoding the Architecture Anthropic Just Made Standard
May 9, 2026 · 3 min read
Anthropic's agent templates for regulated industries matter less for the customer logos than for the orchestration topology underneath: lazy-loaded skills, governed connectors, and isolated subagents.
The Open-Source Agentic AI: Kimi K2.6
April 22, 2026 · 7 min read
An honest read of Moonshot's Kimi K2.6 from someone building production agentic systems: why the open weights matter more than the leaderboard, and where it still falls short.
HITL vs Full Automation: A Decision Framework
March 20, 2024 · 1 min read
When to keep humans in the loop and when to ship fully autonomous agentic systems.