> For the complete documentation index, see [llms.txt](https://docs.riff.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.riff.ai/archive/features-legacy-databutton-web-app-builder/workspace-features/tasks.md).

# Tasks

Tasks is a shared visual board where you and the AI agent collaboratively plan, track, and manage the development of your app. It's your project plan and progress tracker in one place.

How to access: Click the Tasks tab in the workspace top bar.

Key features:

* Create tasks: Add new tasks manually or ask the AI agent to create them
* Task statuses: Track progress with To Do, In Progress, and Done statuses
* Task details: Each task includes title, description, priority, labels, and a complete history
* Task history: View comments, decisions, learnings, and blockers logged by the agent
* Task assignment: Tasks can be assigned to the agent or managed by you
* Filtering: View tasks by status to focus on what matters

How to use:

1. Describe what you want to build to the AI agent
2. The agent will create a task with a clear definition of done
3. Track progress as the agent works through tasks
4. Review task history to understand decisions and progress
5. Mark tasks as done when completed

Tips:

* Start with clear, focused tasks rather than large, vague requests
* Check task history to understand the agent's reasoning and learnings
* Tasks automatically link to code commits for full traceability
* Use task IDs (e.g., ) when discussing specific tasks


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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.riff.ai/archive/features-legacy-databutton-web-app-builder/workspace-features/tasks.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.