Sculptured docs

Run a team

Start a team, follow its work on the Run board, and pass work along again when you need to.

Start a team from the Design board, then follow its work in Run. Agents with no incoming handoffs begin with their Jobs. Other agents wait for upstream results before starting their assignments. This guide covers ordinary handoffs; Workflows explains teams that use stages.

flowchart LR
  D["Design board"] -- "Start team" --> C["Checks: ready to start or things to fix"]
  C -- "Start Claude and Codex agents?" --> L["Agents launch, givers first"]
  L -- "Job as first message" --> W["Agents work"]
  W -- "finished turn" --> H["Handoff to the next agent"]
  H --> W
  W -- "Stop team" --> S["Stopped, history kept"]

Before you start

The project's status, next to Start team at the right of the tab row, reads Draft · ready to start, Draft · N to fix or Running.

Start the team

  1. Press Start team
    It sits at the right of the project's tab row, on every page of the project.
  2. Confirm real agents
    If the team has Claude or Codex agents, Sculptured first asks "Start …?". It names where they run, whose accounts they use and which agent starts first.
  3. Watch the launch
    Agents launch in order, givers before the agents they hand work to. Each one shows launching, then running.
  4. Open the Run board
    The board switches to Run once the team has started. Before then Run is off and says "Run opens once the team has started".

If something goes wrong, the board says "Could not start:" and lists the issues, with a link back to the Design board. While a team runs you can still rename agents, edit their Jobs and move cards. To add, remove or reconnect agents, stop the team first.

The Run board

The Run board draws the running agents and their connections. Open the Agents tab, or press l, to see every agent, including stopped and planned agents. Cards and Logos switch how agents are drawn.

The Run board with three agents: Planner needs you, Builder 1 and Builder 2 are done, with message counts on the arrows

What to look for: each card's status in words, what it last said, its tokens, and the messages observed between agents.
PartWhat it shows
Agent cardName, state, its latest reply ("› …"), tokens, and the time since its last activity. A card that needs you has an Answer button.
Status (tab row)For example "Running · 2 of 3 working" or "Needs you · 1 of 3". Notices such as "history has a gap" show on the board.
Results › Team conversationOne timeline of updates, messages, handoffs, questions and reported results, with a Needs You row.
Results › UsageTokens each agent has used over time: output, cached input read, and context now.
Results › CommunicationsWho talks to whom, message traffic, delivery and read state, and captured payload sizes. See Context and communication.
Results › HistoryEarlier runs of this team, with Download run.
Work evidence (Run board)For a team with a workflow: each item, its stage, its history, and decisions waiting for you.

Click an agent to open its page: Conversation to read it and send it messages, Setup for its design, and Activity for its progress and events. See Control live agents.

What the states mean

Each card shows its state as a symbol and a word, so nothing relies on color alone.

StateMeaning
⚙ workingA turn is in progress.
◉ needs youIt is waiting for your answer, or it needs attention.
▲ stuckIts handoffs cannot go on by themselves. The reason says why.
✓ doneA turn finished since you last looked.
○ idleIts session is open but it is doing nothing.
∅ unknownSculptured cannot see it right now, for example while its computer is offline.

"No active work; sessions are open. Stop team closes them." means every agent is idle. An open session is not working. The full list of states and what moves an agent between them is in Agent states.

How work moves along

Only hands work to arrows move work. Reports to and watches describe intent and send nothing.

Pass work along again

The agent's page shows handoff actions when they apply:

ButtonWhen it showsWhat it does
Hand over againA running agent with agents downstreamSends its latest finished turn to the agents it hands work to. Each agent downstream runs once.
Resend handoffA handoff or Job never reached a running agentSends what it is owed again.
Restart this agentThe agent needs attention, failed or stopped while the team runsRelaunches only this agent. It then gets what it is owed.

If the downstream agents are real Claude or Codex agents, Hand over again first asks "Re-run N agents downstream of …?". Each one runs once and uses your account.

Cost and limits

See Limits and usage for token accounting, budgets and plan usage holds.

Finish or start again

Results › History of a run, as a tree: a box for each agent, Planner, Builder 1 and Builder 2, with its last observed state, its runtime, output tokens and when it launched

What to look for: **Results › History**, the run to show under **Deployment**, and **Download run** to save it as a file. Click an agent's box for its recorded events; **List** shows the same agents as a list.

Next steps