Background Agent
A background agent (or cloud agent) runs a task outside the active chat—on a remote VM, queued worker, or local process—while the user works elsewhere.
Long research, test suites, and multi-file refactors depend on background runs, but users still need progress, stop, and completion receipts.
What it means
The agent session decouples from the foreground UI: work continues with its own logs, tools, and time limits until done, failed, or cancelled.
Why designers should care
Background UX needs persistent status, push or in-app notifications on completion, readable summaries, and one-click open—not “come back and guess if it finished.”
Example
A cloud agent refactors twelve files over eight minutes; the user gets a bell notification, opens an activity summary with diffs, and approves merge from the receipt card.
Common mistakes
- • Background jobs with no cancel or time cap.
- • Completion with no summary—user must re-read entire chat to find outcome.
- • Foreground and background agents conflicting on the same repo without warning.