Subagents

When a task splits into independent pieces, the agent hands them to subagents and works on something else while they run. Each one is a separate job with its own step budget, so a research pass and a repository read can happen at the same time rather than one after the other.

​

The kinds

Research runs shallow or deep. Deep spends more steps and reads more pages. GitHub reads at most 15 files, chosen for relevance rather than crawling everything. Builders only exist in Fast mode. The agent starts up to eight at once from one shared contract, and each owns a disjoint set of files: a write to a file another builder owns is refused. On a Computer they write into the project and may read any file in it, but have no shell, so they cannot install, run or build anything. Without a Computer each file they write becomes its own artifact. They run at low or medium reasoning effort, never higher than the effort you picked, and count toward the same per turn limit as every other subagent.

​

Running in parallel

By default two run at once. Fast mode raises that to eight, Max mode to four, and attaching a Computer raises it to five as well. The agent can change it for a chat if a task genuinely fans out, up to ten. Guards exist so a loop cannot run away: at most 48 subagents per turn, at most eight left running in the background at any moment, and a kind that fails three times in a row is not tried again. Each subagent gets 32 minutes.

​

Watching them

A subagent appears as a card in the conversation rather than a bare tool call, showing how many actions it has taken and how many tokens it has used. Open it and you get the task it was given, a live activity timeline, any files it touched, and its result or its error. The details panel on a message counts subagents dispatched, web research done and pages read.

​

Background subagents

The agent can start a subagent, carry on with something else, and collect the result later. That is what lets it fire three research questions at once and then write one answer from all three. You do not manage this. It is worth knowing about because it explains why the agent sometimes says it is waiting on something.