> ## Documentation Index > Fetch the complete documentation index at: https://docs.mutagent.io/llms.txt > Use this file to discover all available pages before exploring further. # Sub-agents > Dispatch a crew in parallel, watch every agent live in the fleet list, and steer any of them by typing at it. Helix delegates parallel work to sub-agents: the model calls the `Agent` tool, the agent runs in the background, and the session keeps going. The messaging is bidirectional — the session can steer a running agent and read its result, and agents send findings back. You watch and steer all of it from two surfaces: the fleet list and the agent viewer. In the orchestrator, Helix dispatches the crew itself when a stage needs parallel work. In [agent mode](/helix/agent-mode), your agent has the same tools and you can ask for parallel work directly. ## The fleet list Dispatched agents appear under your prompt: ``` ↑↓ select · 1-9 open · enter view · x remove · esc back ⏺ 1 ✓ explore MC Evaluator trace verse 18s · ↓ 72.3k tokens ◯ 3 ⠸ general-purpose MC Builder scaffold — running command… ↻1 · 11s ◯ 5 ⏳ ai-architect queued + 2 more ``` The fleet list under the composer: a finished agent with a checkmark, three agents running commands with live token counts, an overflow row reading + 1 more, and the key hint row.

The fleet list under the composer: a finished agent with a checkmark, three agents running commands with live token counts, an overflow row reading + 1 more, and the key hint row.

Each row carries the agent's name, its dispatch, and live stats. The list shows at most four rows; the rest are counted as `+ N more`, never dropped. The digits are **slots held for an agent's lifetime** — an agent that finishes and ages out never renumbers the ones below it, so `5` opens what it opened a minute ago. | Key | Does | | ------------------------ | ---------------------------------------------------------------------------------------------------- | | `↓` (at an empty prompt) | Activate the list; `↑`/`↓` move, `Enter` opens, `Esc` returns to the prompt. | | `1`–`9` | Open that slot directly, at any time. | | `x` | Remove the selected row. Display only — a running agent keeps running and still delivers its result. | Finished agents linger for a minute, and the clock restarts each time you open or close one, so an agent you keep returning to cannot vanish mid-read. The list steps aside while a picker such as `/model` holds focus. ## The agent viewer Open an agent and its conversation **replaces** the chat — it is not a split pane. The transcript renders with the same components as the main session: tool calls are real cards, markdown renders, diffs render, errors are styled as errors. It updates live while the agent works. The sub-agent viewer replacing the chat: header with agent name and live stats, Bash and Read tool cards, the working line, and a steering instruction typed in the composer.

The sub-agent viewer replacing the chat: header with agent name and live stats, Bash and Read tool cards, the working line, and a steering instruction typed in the composer.

The composer at the bottom is the same editor as the main chat, and **whatever you type steers the agent you are watching**. A steer that cannot land keeps your text in the box and tells you why — an agent that has already finished cannot be steered. `Esc` closes the viewer and returns you to the main conversation; the agent keeps running. ## Failures report as failures An agent that never reached the model — no tokens, no tools, no output — is reported as an error with the reason (model availability, provider credential, rate limits), not as a finished agent with an empty transcript. The dashboard, the session commands, and the working line.