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.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
It tackles the two failure modes that quietly cap coding-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 → value — narrow context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → windows and lack of persistent memory — from someone building agent-native infrastructure at monorepo scale, offering an architectural lens (harnesses, Polygraph) for giving agents the context and continuity they actually need.
Key quotes
“You would have a genius on one side and something deeply deficient on the other. And that's what agents are.”
Victor Savkin
“Agent forget the work. Every session start with a blank slate. The human becomes the memory in this case.”
Victor Savkin
“Polygraph lets you treat complex multi-repo change as if it was a single repo change.”
Victor Savkin
“What you get is an agent with eidetic or photographic memory of your entire organization.”
Victor Savkin
“Every agent can run by every developer contributes to kind of one big this hive mind, right?”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
