An agent harnessThe 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.Full definition → is the software around an AI model that supplies its tools, context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →, memory and permission rules. This essay argues that, as models absorb capabilities once supplied through prompts and scaffolding, engineers can delete some of that surrounding software.
Its prediction is that what remains is a harness for human attentionThe mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.Full definition →: deciding when an 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 → may interrupt, keep working, or needs approval. The essay expects human-facing functions such as permissions, identity, trust and legibility to stay, and says a model that absorbed permissions would have dissolved them. That is the author's forecast of where harness design is heading, not a measured result.
Terms in this piece · Glossary
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 window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
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.
