# Task Management

## Overview

The Task Board allows you to organize and manage tasks your Agent creates. There are two types of tasks you can set up:

1. **Scheduled Tasks**: Time-based tasks that can be one-time or recurring
2. **Long-term Tasks**: Goal-oriented planning with multiple sub-tasks

<figure><img src="/files/VK3s3qPbrc7n7WsdHwvy" alt=""><figcaption></figcaption></figure>

## Scheduled Tasks

Scheduled tasks are time-based reminders that can be either one-time or recurring.

### Types of Scheduled Tasks

* **One-time Task**: Single execution task (e.g., "Send a tweet about the latest crypto news")
* **Recurring Task**: Repeated on a defined schedule (e.g., "Send an email at 3 PM every day")

### Creating Scheduled Tasks

**Example instructions:**

* "Remind me to drink water in one hour"
* "Please remind me to send an email at 3 PM every day"

**Workflow:**

1. Input the instruction
2. Click **Schedule Task**
3. Agent will process and create the task

<figure><img src="/files/MuIbNaZwsvQcO1J1OCE4" alt=""><figcaption></figcaption></figure>

4. View and edit task details:
   * Task Name
   * Task Instruction
   * Task Time
   * Task Type (automatically assigned, not editable)
   * Click **End Task** to cancel the task

<figure><img src="/files/15Rsgwf70lj5jwuZXkVF" alt=""><figcaption></figcaption></figure>

## Long-term Tasks

Long-term tasks are goal-oriented planning tasks that can generate multiple sub-tasks to achieve a specific objective.

### Creating Long-term Tasks

**Example instructions:**

* "Help me operate my Twitter account. I am focused on #AI and #Web3"
* "Please help me plan a Twitter operation. Aim to increase 1,000 followers"

**Workflow:**

1. Input the instruction
2. Click **Long-term Task**

<figure><img src="/files/IVBpKvCgszbWEmmmoPKz" alt=""><figcaption></figcaption></figure>

3. Agent will process and create the task

<figure><img src="/files/yms3h0qBSQkWakpvduTE" alt=""><figcaption></figcaption></figure>

4. View and edit task details:
   * Task Name
   * Task Instruction
   * Task Time
   * Task Type (auto-assigned)
   * Click **End Task** to stop the process

<figure><img src="/files/NSuZ00IwJoohlxKVB7Yc" alt=""><figcaption></figcaption></figure>

### Task Hierarchy

Long-term tasks follow a hierarchical structure:

* **Parent Task**: Main goal or long-term objective
* **Sub-task**: Specific actions generated from the parent task

{% hint style="warning" %}
**Note**: Ending the parent task will automatically terminate all associated sub-tasks.
{% endhint %}

## Notifications

### Execution Notification

After the agent executes a task, the user will receive a notification:

* After completing a task, the agent will proactively provide feedback in the session where the task was originally assigned.

<figure><img src="/files/TjYTl1h9wSMbNLGbYGUh" alt=""><figcaption></figcaption></figure>

* After each task is executed, a task session will automatically appear, displaying a notification along with the task logs.

<figure><img src="/files/49Al7ydY9L7AtOaS28Ht" alt=""><figcaption></figcaption></figure>

### Notification Center

The Notification Center keeps you updated on task execution:

* Displays task execution updates from the Agent
* Click a notification to view task details in the TaskBoard

<figure><img src="/files/FmtzhFDwvFhRs7JE0hUu" alt=""><figcaption></figcaption></figure>

## Next Steps

* [Learn about Knowledge Packs](/world3/how-to-guides/ai-agent-portal/core-features/knowledge-packs.md) to enhance your agent's expertise
* [Explore available Skill Plugins](/world3/how-to-guides/ai-agent-portal/core-features/skills.md) to expand your agent's capabilities


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.world3.ai/world3/how-to-guides/ai-agent-portal/core-features/task-management.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.