Swarm lets a Mind split the work of one message across parallel sub-agents. Turn it on for a message, watch the agents work in the tree, and read what each one reports.
The toggle appears only when the Mind includes swarm. A Mind manager switches it on with Parallel sub-agents on the Mind's AI Config tab; see Choose models and AI behaviour.
With the toggle on, the Mind may start parallel sub-agents for that message. A spawn starts 1 to 5 agents, and the Mind decides when a message is worth splitting. The Mind's Max concurrent agents setting, from 1 to 25, caps how many agents run at the same time in one chat.
While at least one agent is queued, running or waiting for you, a Swarm bar sits above the message box. It counts the agents, for example 1 waiting for you · 2 running · 1 queued, and it shows how long the longest-running agent has been working. When agents wait for you and none of them are running, the bar takes a warning tone. The bar disappears once every agent has finished, failed or stopped.
Each agent node shows its name, its status, its elapsed time and its token count, for example 12.3K tok. A line to an agent animates while that agent is still live. The window's footer lists the six agent states: Queued, Running, Waiting for you, Completed, Failed and Stopped. A tree goes at most three levels deep.
If no agent has started yet, the window reads No swarm agents yet and suggests Turn on the swarm toggle in the composer and ask the mind to parallelize its work.
Swarm work also appears as step cards in the answer. A spawn card reads Spawning 2 agents… while the agents start, then Spawned 2 agents. Other steps read Swarm status, Agent stopped or Agent resumed. When a step fails, the card says so, for example Swarm agents not spawned, Message not delivered, Agent not stopped, Agent not resumed, Swarm status unavailable or Swarm report failed.
For the chat's own working, waiting and connection states, see Chat states and recovery.
An agent that needs something from you shows the status Waiting for you. It may need an answer or an approval before it can continue.
A notice appears: the agent's name in quotation marks, followed by needs your decision. When the name is not known, it reads A swarm agent needs your decision. Click Open to jump to the agent's chat. The notice is skipped when you already have that chat open. Agents that wait for you still count as live.
When agents finish, the main chat gets a row from the run. Its chip reads Filed by swarm, it counts what came back, for example 2 agents reported, and View report opens the full report. When there is no count, the row reads Report filed.
The Swarm Report shows one section per agent, with its summary and the artifacts it produced. A SQL badge marks SQL artifacts. Click an artifact chip to open the artifact; on desktop the report closes behind it. If an artifact cannot be opened, the chip is dimmed and its tooltip reads Artifact not available. If nothing was recorded, the report reads No report details available. A stopped agent's section says Stopped before filing a report.
Every swarm step also appears in Tool History (Ctrl+Shift+H). Open a step to read more: Requested agents lists the full task each agent received, Swarm status shows a table with every agent's Status, Depth and Tokens, and Reports holds the report content.
Click an agent in the tree to open its chat. Messages that the parent chat delivered are marked Task from parent.
The Delivered artifacts card shows what the parent sent with the agent, for example Delivered artifacts (3). A + briefing badge means a briefing came along. A chip marked no data attached means the parent left result rows out of the delivery. Hover the chip to read why:
If the card has no details, it reads No artifact details available.
Instructions that the parent writes to an agent stay out of the visible chat. The Delivered artifacts card is the record of what arrived.
An agent's chat follows the main conversation for some settings:
/ and / are not available in an agent's chat.No. The toggle only lets the Mind split the work of that message. The Mind decides when it needs sub-agents, and it starts 1 to 5 of them when it does.
The Mind decides. A single spawn starts 1 to 5 agents. How many run at the same time is set on the Mind with Max concurrent agents, from 1 to 25 (the default is 10). See Choose models and AI behaviour.
Open Tool History and open the spawn step. Requested agents lists each agent with its full task text and any artifacts attached to it.
The agent is blocked until you answer it or approve something. Open its chat from the tree, or click Open in the notice, and answer there.
The agent stops, and every agent below it stops with it. Anything the agent was waiting for is settled too: a waiting approval is declined with "The agent was stopped before a decision was made." The rest of the tree keeps running. To stop everything, use Stop all.
Yes, if its status is Stopped or Failed. Use Resume agent {name} on its node in the tree.
A tree goes at most three levels deep.
Click View report on the Filed by swarm row to open the Swarm Report. For the steps behind it, open the swarm entries in Tool History.
It follows the main conversation for some settings: the visibility switch is locked (Visibility is controlled by the parent chat), change acceptance is set on the main chat, and / and / are not available. See Chat commands, shortcuts and privacy.
The parent did not attach result rows for it, usually because the result was large or wide, or because the query never ran; the agent then runs the query itself. Hover the chip in the Delivered artifacts card to read the exact reason.
The Swarm bar disappears once no agent is queued, running or waiting for you. The Filed by swarm row and the Swarm Report stay in the chat.