ML//agent//agent-computer interface

An **Agent-Computer Interface (ACI)** is the set of commands and feedback formats through which a language-model agent operates a computer. It plays the role that a GUI or shell plays for a human, but it is designed around a model's ability to generate structured actions and interpret serialized observations. The term was introduced by [SWE-agent](https://arxiv.org/abs/2405.15793) in 2024.

An Agent-Computer Interface (ACI) is the set of commands and feedback formats through which a language-model agent operates a computer. It plays the role that a GUI or shell plays for a human, but it is designed around a model's ability to generate structured actions and interpret serialized observations. The term was introduced by SWE-agent in 2024.

Action side: Names, schemas, editing primitives and validation rules determine which operations the model can express reliably.

Observation side: File viewers, search summaries, command feedback and errors determine which distinctions the model can perceive.

SWE-agent examples: A 100-line file view beat larger windows; listing only files containing search matches beat richer match output; an explicit success message removed ambiguity when a command returned nothing.

Boundary: The ACI is the exposed interaction surface. The harness is the wider runtime that owns context assembly, execution, permissions and lifecycle.

Why it matters: Giving two agents access to the same computer does not give them the same usable computer. Interface design changes the task they can effectively solve.