> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jinba.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Tasks (scheduled runs)

> Have an agent run a fixed instruction on a schedule and review each run afterwards

**Tasks** let you run work without chatting: schedule an agent to run a fixed instruction on a cadence — or once, at a set time — and review each run's result afterwards. Open the page from "**Tasks**" in the sidebar.

A task is made of three things:

| Part                     | What it is                                                                                   |
| ------------------------ | -------------------------------------------------------------------------------------------- |
| **Agent**                | The agent that runs — a specific agent, or the workspace default                             |
| **Instruction (prompt)** | What the AI does on each run                                                                 |
| **Schedule**             | "**Recurring**" (a cron cadence) or "**One-time**" (a single date and time), with a timezone |

## Creating a task

<Steps>
  <Step title="Open the form">
    Press "**New task**" on the Tasks page. Suggestion chips offer common starting points.
  </Step>

  <Step title="Describe the work">
    Enter a **title**, write the **instruction** the AI should follow on each run, and pick the **agent to run**.
  </Step>

  <Step title="Set the schedule">
    Choose "**Recurring**" or "**One-time**." For a recurring task, describe the cadence in words — "every weekday at 10:30," "every 15 minutes" — and the AI converts it into a cron expression, or fill in the five cron fields (minute / hour / day of month / month / day of week) directly. The form shows the resulting cadence in plain language along with the next run time, so you can check it before saving; if your phrasing can't be read as a schedule, the form says so and leaves the fields for you to set. Pick the **timezone** the schedule follows. A one-time task takes a single "**Run at**" date and time instead.
  </Step>

  <Step title="Create">
    Press "**Create**." The task appears in the list with its schedule and next run time.
  </Step>
</Steps>

<Tip>
  A task's instruction runs unattended — the AI cannot ask you mid-run what you meant. Write it so it stands alone, the way you would brief a colleague who works while you are away. You can always ask the AI in a chat to help you draft it.
</Tip>

## Runs and review

Each firing produces a run whose reply is captured as a normal chat thread — open a run from the task's history to read the result, and continue the conversation there if you want follow-ups.

* The history in the task's detail is paged **20 runs at a time**, newest first, with "Previous" / "Next" controls
* Failed runs are flagged on the task's row so they are easy to spot
* "**Run now**" fires the task immediately, without waiting for the schedule

## The Tasks page

The tasks are listed on the left — title, agent, schedule, last run, and next run — and selecting one shows its run history and instruction in the column beside the list. When the window is too narrow for both, the detail opens as a drawer over the list instead. Drag the divider between the two to resize the list; the choice is remembered on that device.

## Editing, pausing, and deleting

"**Edit**" opens in place inside the detail, with a back control to return.

* The **title, schedule, and timezone** can be changed by the task's creator or a workspace owner
* The **instruction and the agent** can be changed only by the task's **creator** — a run executes as the creator, using their connector access, so nobody else can change what runs on their behalf
* Changes apply from the next run onward. Runs already in the history were produced by the previous instruction
* A task can be toggled between **enabled** and **disabled** without deleting it, and deleted outright (deleting stops its scheduled runs and cannot be undone)

<Note>
  Two things can happen without you doing them. A task **disables itself** when it can no longer run as configured — its creator left the workspace, or the agent is no longer shared with them; fix the cause, then re-enable it. And **changing a task's agent starts a fresh review thread**: the next run opens a new chat instead of continuing the old one, though earlier runs stay listed and readable.
</Note>

<Note>
  If there is no "**Tasks**" entry in your sidebar, the feature is not enabled in your environment. The AI also has no way to create or change tasks from a chat — it can help you write the instruction, but the task itself is set up on the Tasks page.
</Note>