Agents

Agentic operating systems, Claude Code workflows, hooks, memory, review, and multi-agent work.

AgentsJul 9, 20268 min read

AI Coding Feels Magical Until The Project Gets Serious

AI coding breaks when the work needs memory, handoffs, evidence, review, and recovery. That is an operating-system problem.

AgentsJul 9, 20267 min read

CLAUDE.md can give context, but serious agentic work needs hooks, validators, ledgers, and review gates that do not depend on model memory.

AgentsJul 9, 20268 min read

Premium models should plan, decide, review, and escalate. Cheaper workers should handle bounded tasks that can be checked.