The Half Life of Agent Infrastructure — Ben Kus, Box
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
If AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → infrastructure decays in months, 'pick a stack and go deep' is the wrong default: build swappable abstractions, switch only when evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → sets justify it, and review AI choices on a fixed clock — Box uses six months.
videoGuardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPI
videoFrom Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironclad
videoAgents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan
videoAgentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe
