Agents
Agent status, queues, handoffs and human-in-the-loop approvals.
Components
8 components availableStatus for an AI agent working on its own — running, waiting on you, completed or failed, with what it did last.
Approval RequestThe human-in-the-loop confirmation — what the agent wants to do, the exact details, and allow or deny before it acts.
Approval GateThe approval card as a lifecycle: a decision that survives a closed tab, is idempotent across two open ones, and says what happened when it lands after the request expired.
Agent PlanThe checklist an agent writes for itself and then edits mid-run — steps added, skipped and re-ordered, without the list jumping under the reader.
Agent HandoffOne agent passing work to another — who asked, what was carried across, and what the receiving agent was not told.
Agent Run TimelineThe activity log for a long agent run — collapsible success clusters, retry-linked events, approval gates in place, and a follow that respects the reader.
Approval CardA review card for commands, clarifying questions and short plans, with a visible decision state.
Agent Task ListA collapsible agent to-do list with done, active and pending task states.
Patterns using Agents
Complete interfaces composed from these components.
A coding run with agent status, tool calls, diffs and a human-in-the-loop approval gate.
Open pattern →Structured Extraction & ReviewUpload a document, watch fields fill in, then review the flagged ones — per-field confidence, corrections that keep the original, export earned.
Open pattern →Multi-agent Ops ConsoleWatch a fleet of agents at once — parallel statuses, an inspectable handoff, a waiting approval, a failed child run, and per-run plus fleet cost.
Open pattern →Customer Support CopilotGrounded reply drafts with citations, honest low-confidence answers, inline corrections, an approval gate on refunds, and a rating row on every draft.
Open pattern →