How Bot works

A bot’s turn is a tool loop on a computer. Most of it is invisible by design: the conversation shows only the messages the bot chose to send you, the questions it asked, the notifications it raised, and the credentials it requested. The screen on the Computer rail shows the rest.

​

What you see

Four tools produce rows in the conversation, and each persists as its own row: Listing the conversation returns only these user-visible kinds. Plain assistant text outside them is dropped, not rewritten into a canned message — so a bot that has nothing to say says nothing. Parked steps show as approval widgets; see Approvals.

​

When a turn stops

There is no round counter. Bot does not inherit Chat’s eight-round budget — a computer task legitimately takes many steps.

​

Background tasks and subagents

task runs work in the background and reports task_started / task_progress / task_completed or task_failed. Subagents cannot send_to_user and cannot nest another task; everything flows back through the parent bot, which decides what to tell you. See Tools.

​

Waking the guest

An active turn on a bot whose Cloud guest has hibernated resumes the guest before the model is prompted. The bot always starts a turn with its shell and desktop available; the prompt never tells the model to apologise for missing a computer. See Computer.

​

Computer use, precisely

The planner describes the control it wants — the Save button in the dialog — and a second inference call returns framebuffer coordinates for grounded_click. The planner never guesses raw pixels. Screenshots feed the next step.

​

Compared with Chat and Code

See How Chat works and How Code works.

​

Related

• Tools — the catalog behind the loop.
• Approvals — what parks, and what does not.
• Computer — the guest the loop runs on.
• Bot troubleshooting — turns that stop, and why.