> ## Documentation Index
> Fetch the complete documentation index at: https://docs.marketer.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Specialists
> Route a request, open the Agents workbench, and inspect each specialist's state, tasks, outputs, and sources.
The Marketing Agent coordinates the conversation. Specialists contribute focused work such as research, campaign planning, creative direction, or creative generation. The **Agents** workbench makes that coordination visible without forcing you to reconstruct it from chat messages.
Use the workbench to answer three questions: who owns the current step, what did that specialist produce, and what still blocks the overall result?
## Choose how the request is routed
The agent control in the composer supports two paths:
* Keep the automatic route selected when you want the Marketing Agent to choose a perspective for each turn. It appears as **Orchestrator** on Home; the selector's **Auto** row says **Routes each request**.
* Select a specialist shown in the menu when you want to keep that specialist's perspective for the conversation.
The available specialist names come from the current workspace. Selecting one changes the conversational perspective. A longer run still starts only when Marketer creates the task and you select the run control on a displayed proposal.
For multi-step work, describe the result rather than trying to assign every internal handoff yourself:
```text theme={null}
Build a launch plan around the attached product and our strongest approved
differentiator. Ground the positioning in current Brand Profile and customer
evidence, develop the campaign sequence, and return a launch checklist.
Prepare creative generation as a reviewable plan before running it.
```
## Review the run before it starts
When Marketer proposes coordinated work, the proposal lists the steps it intends to run.
Read the plan for evidence collection, production, ranking, and the final deliverable. Proposal controls vary:
* A named specialist can show **Cancel**, **Edit**, and **Accept & Run**.
* Creative Pipeline can show **Cancel**, **Edit**, and **Approve & Run**.
* Another task plan can show **Cancel**, **Edit brief**, and **Run it**.
Use the edit branch to change the goal, steps, inputs, output count, or review boundary. Use the displayed run control only when the plan should start as shown.
This approval starts the listed work. It does not grant blanket authority for later changes to connected accounts.
## Open the Agents workbench
After work starts, select the **Open Agents** control on the right edge of the conversation. The compact sidebench shows active and recent agent work. Select **More** to open the full overview.
Read the overview from top to bottom:
| What you see | What it means | What to do |
| ----------------------- | -------------------------------------------- | ---------------------------------------------------------------- |
| **Active** | Work that is queued, working, or waiting | Select the row to inspect its current state and task. |
| **Done** | Completed, partial, failed, or canceled work | Open the row to review the result, preserved output, or failure. |
| Specialist name | The focused identity responsible for the run | Compare it with the task you expected that specialist to own. |
| Description | The run goal or latest useful summary | Use it to distinguish similar specialist runs. |
| Relative time or status | Recency and lifecycle context | Confirm you opened the current run rather than an older one. |
An orchestrated family can contain a coordinating run, sibling specialists, and nested specialist work. The overview groups related runs so you can trace the family without assuming every row is independent.
## Inspect one specialist
Select a row in the overview. The header changes to a breadcrumb beginning with **Agents**, followed by the selected specialist. The detail body shows the current or final run content.
For a coordinated plan, the sidebench can expose:
* **Tasks:** the plan steps and whether each is pending, active, done, or blocked.
* **Outputs:** artifacts or result links produced by the run family.
* **Sources:** the linked evidence made available for inspection.
Use the back control to return to the overview. Use the open-detail icon when you want the full Activity detail page for that run.
## Follow a specialist into nested work
A specialist can open a nested pipeline or result. Select the specialist row, then select the nested work from its detail instead of stopping at the parent status.
Use this review path:
1. Confirm every breadcrumb level matches the intended agent family and nested run.
2. Compare the top-level run state with the nested step states; completed nested steps do not necessarily mean the parent has stopped working.
3. Read the result summary and open any linked output, not only the step checks.
4. Check product identity, claims, brand direction, format, and review criteria.
5. Follow any **Outputs** link to **Studio** or **Assets** and confirm the item exists there.
6. Return to the conversation when you want to revise the brief or request a new direction.
The specialist result explains what its branch produced. The conversation remains the place where the Marketing Agent combines branches into the requested final answer.
### Stop work that is no longer needed
When **Stop** is visible in a running specialist or pipeline detail, select it only when the objective should no longer continue. Marketer requests cancellation for that run and its child work, and the control changes to **Stopping…** while the request settles.
Stay on the same detail until the run shows **Canceled**. Do not start replacement work while it is still stopping, because active child work may not have reached its terminal state yet. If **Stop** is absent, the run may already be terminal or your workspace role may not allow changes.
## Handle each specialist state
### Working
Open the row to see the active goal or step. A specialist can remain active while a sibling is already done. Wait for the combined result unless the active row requests input.
### Waiting
Read the detail to identify what is missing. If it needs a fact or constraint, answer in the originating conversation. If it needs a recorded decision, open **Awaiting action**.
### Completed
Open the output and sources. A completed research branch may provide evidence; a completed creative branch may provide an artifact. Neither is automatically the entire requested result.
### Partially completed
Determine which branch produced usable work and which branch did not. Preserve supported output and ask the Marketing Agent to reconcile the missing part.
### Failed
Open the failed row before retrying. Check the last successful step, error, required connection, and whether sibling outputs are still usable. Retry the failed branch only when the cause is resolved.
### Canceled
Treat the run as stopped. Start a revised run from the conversation if the deliverable is still needed; do not assume a canceled branch will resume.
## Reconcile multiple specialist results
When specialists return different recommendations, bring them back to one decision frame in the conversation:
```text theme={null}
Reconcile the campaign and creative recommendations against the same launch
objective, audience, date context, and approved product claims. Identify the
evidence for each disagreement, preserve uncertainty, and return one ranked
plan with explicit review criteria. Do not launch anything.
```
Then verify the combined result:
* Every conclusion maps to an output or source you can inspect.
* Conflicting measurement frames are made explicit.
* Generated claims match approved product and brand context.
* A recommendation is not presented as an applied change.
* The final result answers the original deliverable, not only one specialist's branch.
Specialist identity and completion state do not prove a claim. Inspect the source or output behind material recommendations, especially those affecting spend or customer-facing creative.
## Next step
Review the exact proposal variant before a specialist run starts.
Connect specialist state to the task's current step and terminal result.
Resolve an approval that pauses a specialist or coordinated run.
Continue from the run output into Briefs, Studio, and Assets.
Return to the original request, attachments, and decisions.
## Related topics
- [Chat and context](/working-with-marketer/chat-and-context.md)
- [Home and the composer](/working-with-marketer/home-and-composer.md)
- [Task control and recovery](/working-with-marketer/task-control-and-recovery.md)
- [Questions and approvals](/working-with-marketer/questions-and-approvals.md)
- [Working with Marketer](/working-with-marketer/overview.md)