How a session starts

What Ara puts behind your task before a model sees it.
Ver como Markdown

Sending a task does not hand your prompt straight to a model. Ara starts the Brain with scoped control-plane tools while it prepares Hands in parallel.

What this means day to day

You noticeWhy
Follow-ups answer faster than the first messageThey can reuse the live Brain and Hands binding
The first reply arrives before commands can runBrain inference overlaps Hands preparation
A Device disconnectsbash and repl disappear; scoped Ara control tools remain

Why workspace preparation takes as long as it does

Preparing the workspace is not one step. Hands checks out the repository, fetches the default and working branches, loads any additional context repositories, and makes sure the required toolchain is present.

How long that takes is mostly a property of your repository rather than of Ara: a large repository with a long history and many files takes longer to clone than a small one, and that difference is the single biggest factor in how quickly a fresh sandbox is ready. Ara now records how long each of those steps took individually, so a slow start can be attributed to the specific step responsible instead of reported as one opaque total.

This is measurement only. It does not change how a session starts, what runs inside the sandbox, or the order in which anything happens.