Topic
Runtime, memory, tooling, verification, and operating layers for long-running agent systems.
Agents become useful only when their infrastructure can manage state, cost, reliability, and recovery.
AI Systems EngineeringTool-Agent Reward HackingVerification Economics
A research field note reframing cognitive load as the acceptance cost of code, with a worked Operator Load Budget audit for AI-generated patches and human review bandwidth.
A field note showing why verifier accept rate can dominate the other levers in cost-per-correct-answer economics.
Results are local, static, and index the same public surfaces exposed to crawlers.