Skip to content

orchestrate is the one agent that orchestrates, a workflow is a plan it is started on, and the live bench compares it with build on the same tasks

Decision 888 · accepted · 2026-10-12 · issue #554 · supersedes 850

The decision

  • One agent orchestrates: orchestrate. The workflow built-in is gone. orchestrate takes its model, expensive, which is the default model unless a person names a dearer one (models.expensive), so nothing changes for anyone who has not, and its paragraph: a prompt that is a numbered step list is a workflow, the steps are the plan, [you] is its own step, parallel steps may go out together, and no step, least of all a test or verify step, is dropped without saying why. The rendered plan says the rest, as it did.
  • A workflow is a plan orchestrate is started on. Troupe.Workflow.agent/0 names the runner, and session.create with workflow starts it on Troupe.Workflow.plan/2's prompt. A client that names profile: "workflow", the old runner's name, gets orchestrate (Troupe.Workflow.agent/1); one that names another agent runs the plan there, as before. Worktrees, approvals, budgets and resume apply unchanged, since running a workflow is still starting a session (Decision 648).
  • /workflow is a built-in command in the harness's table and the terminal client's, since no agent row carries it any more; the terminal starts the branch on orchestrate, in a worktree of its own, its window still workflow-<n>. The desktop app starts no branch and lists it as one it cannot run.
  • What this replaces. Decision 850's choice of two profiles (the rest of 850 stands), TUI Decision 87's "the workflow agent" (its reasoning holds for orchestrate: an expensive orchestrator that cannot write and owns only the decisions), and TUI Decision 104's "the workflow agent's first input" (now orchestrate's).
  • Not chosen. Two profiles with a stated boundary: the step list was the only thing the workflow agent had that orchestrate did not, and a list is data the plan renders, not a second agent to keep in step. workflow as the name of the one agent: orchestrate is the name #554 and Decision 850 gave the profile people choose, and workflow names the plan. orchestrate handing a multi-step task to a workflow through a tool: a second session for what a task list already does.
  • A repository's own .troupe/agents/workflow.md is an ordinary primary now, which /workflow does not run; one that changed how workflows run copies orchestrate.md instead.

The bench

  • The same outcome at two and a half to three times the cost. Every run of both agents got the work done and held every check. orchestrate cost 2.5, 2.9 and 3.1 times what build did, made twice the model calls (2.5 times on follow_steps), and took 2.4 to 2.8 times as long.
  • So build stays the default and orchestrate is suggested nowhere. On these tasks it buys nothing a person can see. What the bench does not have is a task large enough that build's own context grows past what a few briefs cost, or one where a reviewer catches what the writer missed; every task here takes build three or four calls.

Which to use

build for a change you would make yourself, which on the bench is every one of them; /workflow when a repository has written down the steps a change goes through (a release, a migration) and wants each owned by a subagent, with a reviewer at the end, in a worktree of its own; orchestrate on your own words when you want that shape without a declared list, knowing that on small tasks it costs about three times as much. The terminal client's README says the same, with these numbers.

Governs: apps/troupe_core/lib/troupe/workflow.ex, apps/troupe_core/lib/troupe/commands.ex, apps/troupe_gateway/lib/troupe/gateway/dispatch.ex, apps/troupe_core/lib/troupe/bench/live_scenarios.ex, clients/tui/lib/troupe/client/daemon.ex, clients/tui/lib/troupe/ui/tui/server.ex