# March 2023 third release

## Enhancements to manual annotation workflow

<figure><img src="/files/YAKqxZNVUTY9IcYHMfRZ" alt=""><figcaption></figcaption></figure>

We have improved the manual annotation process by preselecting the composite that you have highlighted, making it easier to add missing entities. We have also added numbers next to the composites names for easier identification.

## Task description

<figure><img src="/files/TduwEGHaOkPvegDN4K05" alt=""><figcaption></figcaption></figure>

Task descriptions can now be viewed alongside other task details, allowing for better communication and collaboration among team members. This feature can be especially helpful for noting special details for example "Fixing training data to recognize the name entity better".

<figure><img src="/files/3H5ZHjH1TuBprRZfYg1j" alt=""><figcaption></figcaption></figure>

## **Table annotation graduating to "**�� **Stable"**

<figure><img src="/files/VxI9GepyEUpCShdMppxD" alt=""><figcaption></figcaption></figure>

Our table annotation feature has graduated to "🏭 Stable", which means it is now a fully supported part of the platform. You can easily annotate tabular data, and save time with its efficient interface. You can now rely on it for your annotation efforts without any worry of instability.

{% content-ref url="/pages/BcGsa1ZjCJlQBZd2uGg1" %}
[Table annotation](/getting-started/processing-documents/labelling-of-training-data/entity-extraction/table-annotation.md)
{% endcontent-ref %}

<figure><img src="/files/3H5ZHjH1TuBprRZfYg1j" alt=""><figcaption></figcaption></figure>

## **Copy project graduating to "**�� **Stable"**

<figure><img src="/files/Ybw7ytGrANxSh9mV1E8C" alt=""><figcaption></figcaption></figure>

Our copy project feature has also graduated to "🏭 Stable". This feature allows you to duplicate projects with ease, making it simple to setup similar projects. You can trust this feature to work reliably as it is now a fully supported part of the platform.

{% content-ref url="/pages/ZdUh2WEVZb9duzOOgDFQ" %}
[Project settings](/project/project-settings.md)
{% endcontent-ref %}


---

# 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-old.app.metamaze.eu/release-notes/release-archive/release-archive-2023/march-2023-third-release.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.