agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
Why it matters
Names the layers that separate a browser-agent demo from a production one — security, caching, identity and credential brokering, agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → memory — and argues why the tool surface should stay small and match what models already know from pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition →.
