> ## Documentation Index
> Fetch the complete documentation index at: https://cubed3-docs-dashboard-link-target-honored.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Scheduled Tasks

> Save a natural-language agent prompt and have Cube run it automatically on a schedule, producing a chat thread for each run.

Scheduled Tasks let you run tasks on a schedule — or whenever you need them.
Save a natural-language prompt for the
[agent](/docs/explore-analyze/analytics-chat) and have Cube run it
automatically on a schedule or on demand. Each run produces a chat thread
you can open later to read the agent's answer. You can also ask the agent to create a
scheduled task for you from any of your chats.

For example, you might schedule a task to *"every weekday at 9am, summarize
yesterday's signups, flag anything anomalous, and email me the results"* and
review the summary each morning.

Scheduled Tasks are **scoped to a deployment** — each task belongs to the
deployment it was created in.

## Where to find it

In the deployment sidebar, open **Scheduled** (the clock icon, below
**Explore**). The page lists the deployment's tasks with their name,
schedule, status, and description, and is searchable.

## Anatomy of a task

A task has:

* **Name** (required) — how the task appears in the list.
* **Description** (optional) — a short summary shown in the list.
* **Instructions** (required) — the natural-language prompt the agent runs on
  each execution.
* **Schedule** — how often the task runs (see below).
* **Enabled** — a toggle to activate or pause a scheduled task.

## Schedule options

Scheduled Tasks use the same schedule editor as
[dashboard scheduled refresh](/docs/explore-analyze/scheduled-refreshes),
offering these frequencies:

* **Manual** — no schedule; the task runs only when you trigger it with
  **Run now**.
* **Hourly**, **Daily**, **Weekly** (with a day of the week), and **Monthly**
  (with a day of the month) — each with a time picker.
* **Custom** — a raw cron expression for full control.

A **timezone** selector (defaulting to your browser's timezone) controls when
the schedule fires; it is stored per task.

## Managing tasks

From the list, you can:

* **Create** a new task. The **New task** button is a dropdown with two
  options:
  * **Create with agent** — opens a new Analytics Chat pre-seeded with a
    message asking the agent to explain scheduled tasks and interview you
    about what the task should do and when it should run. The agent then
    creates the task for you (see
    [Managing tasks from chat](#managing-tasks-from-chat)).
  * **Set up manually** — opens the create dialog where you fill in the
    task's details yourself.
* **Edit** an existing task's instructions, schedule, or details.
* **Enable / Pause** a scheduled task to control whether it runs on schedule.
* **Run now** — trigger a one-off run immediately. This works for both manual
  and scheduled tasks. Triggering a run shows a notification with a **View**
  link straight to the run's chat thread, and the thread appears in the
  Recent Chats sidebar immediately.
* **Delete** a task. Deleting removes its schedule and stops all future runs.

## Task detail page

Clicking a task in the list opens its detail page. The header shows a
breadcrumb back to Scheduled Tasks, the task name, a status tag (**Manual**,
**Active**, or **Paused**), and the description, along with actions to
**Edit** (pencil), **Delete** (trash), and a primary **Run now** button.

The page shows:

* **History** — the task's runs, newest first. Each entry is a timestamped
  link that opens that run's chat thread. Currently-executing runs
  show a **Running** tag, and failed runs a **Failed** tag. The list shows
  the latest 50 runs; a "Showing the latest 50 runs" note appears once the
  cap is hit.
* **Instructions** — the task's prompt.
* **Repeats** — the schedule in plain language.

## Reading the output

Each run creates a chat thread containing the agent's response. Open the
thread in [Analytics Chat](/docs/explore-analyze/analytics-chat) to read the
full answer, ask follow-up questions, or
[save results to a Workbook](/docs/explore-analyze/workbooks).
Scheduled-run threads are marked in the Recent Chats sidebar with a clock
icon (hover over it to see the "Scheduled task" tooltip).

A run shows as **Running** while it executes, then completes or fails. A
failed run's thread shows a failure notice instead of an empty thread.

The task runs headlessly under the security context of the user who created
it, so it sees exactly the data that user can access.

### What the agent can do in a scheduled run

Beyond querying the semantic model, the agent in a scheduled run can:

* **Send email to workspace members** — for example, *"summarize yesterday's
  signups and email the summary to me."* This requires the agent email tool
  to be enabled for the workspace; recipients are restricted to workspace
  members.
* **Use web search**.
* **Create and update reports, workbooks, and dashboards**, using the task
  creator's permissions.

Scheduled runs do not yet have data-model access — editing the semantic
layer is currently available only in interactive chat.

## Managing tasks from chat

You can also create and manage Scheduled Tasks conversationally in
[Analytics Chat](/docs/explore-analyze/analytics-chat) — from any chat, not
just ones started with **Create with agent** (that menu option simply opens
a chat pre-seeded for this flow). Ask the agent to schedule, update, list,
or delete tasks in plain language — for example, *"schedule a daily summary
of yesterday's signups at 9am"* or *"list my scheduled tasks."*

The agent's actions render in the chat as labeled steps with a clock icon —
*"Creating scheduled task…"* / *"Created scheduled task"*, *"Listed
scheduled tasks"*, *"Updated scheduled task"*, and *"Deleted scheduled
task"*.

The agent manages task definitions: when listing tasks, it can report each
task's id, name, description, schedule, timezone, and enabled state. A
task's run history lives on its [detail page](#task-detail-page).