> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/assisted-labeling/real-time-assisted-labeling.md).
# Real-time Assisted Labeling
Real-time assisted labeling enables automatic labeling without requiring configuration or AI knowledge. This extension simplifies the workflow and improves labeling speed and accuracy.
{% hint style="info" %}
**Supported labeling types:** Span labeling.
{% endhint %}
## Introduction
**Real-time assisted labeling** is a feature that provides label suggestions while you are labeling data. It helps you label data more quickly by showing predictions in real time.
Previously, users needed to go through several settings to enable assisted labeling, which could take time and effort. But now, you do not need to set up many configurations. The system generates suggestions as you work, which you can accept or reject.
## Key features
* **Real-time predictions**: Provides labeling suggestions as users work, allowing them to accept or reject predictions immediately.
* **Simplified workflow**: Removes the need for extensive configuration and enables quick setup.
* **Batch processing**: Displays predictions in groups, allowing users to review multiple labels at once and improve efficiency.
## Quick start guide
{% hint style="info" %}
This feature is currently in beta. Please contact to enable this feature.
{% endhint %}
**Real-time assisted labeling** is enabled by default. If it is disabled, follow these steps:
1. In a project, click the gear icon in the extension panel on the right to open the **Manage extension** dialog.
2. Enable **Real-time assisted labeling**.
3. Ensure **Automatically suggest labels** is enabled.
Once enabled, you can start labeling:
1. Begin labeling your data normally. No additional configuration is required.
2. The system will start generating predictions once enough labels are provided.
3. Review predictions as they appear and accept or reject them.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.datasaur.ai/assisted-labeling/real-time-assisted-labeling.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
