> For the complete documentation index, see [llms.txt](https://docs.tryprotege.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tryprotege.com/review/review-tool-concepts/document-review/conducting-reviews/office-365-word.md).

# Office 365 Word

**Prerequisite:** [Office 365](/review/getting-started/document-editor-installation/office-365.md)

**Open**: **the Plug-In:**

1. Create a new Word Document and enter the text you want reviewed. Alternatively, you can open an existing Word Document.
2. Navigate to the Home Ribbon tab, select "Add In", and "Protege AI".

<figure><img src="/files/Ok0ePXhkjNQ4nagqCJgi" alt=""><figcaption></figcaption></figure>

**Log In:**

If you haven't logged in previously, you'll be prompted to do so at this point. After opening the Protege AI extension, press "Sign In". Enter your credentials. Once logged in, you'll have full access to existing feedback for that document or create a new document for scanning.

**Setting the Document Review Type:**

When a new document is opened for review, setting the document review type is a process designed to tell the AI which evaluation to do for your content. You'll be prompted to put the name of the document and the Document Review Type that is set up for the company. The name of the document will be used to create an associated task for your team's progress tracking.

**Change** **the Document Review Type:**

You can change the Document Review Type by pressing the ⚙️ icon on the sidebar, and selecting "Edit Project." After that press Quick Scan again to see the new feedback.

For a better understanding of Document Review, see [Document Review](/review/review-tool-concepts/document-review.md),

**Scan Process and Processing Feedback:**

The scan process in Protege Counsel is a comprehensive evaluation mechanism designed to identify and mitigate legal risks associated with your content. From the sidebar in a document, run Quick Scan to get the results of the evaluation. Depending on the length of the document, it may take several seconds to start seeing the feedback populate.\
\
There are three categories of Feedback:

{% content-ref url="/pages/vjqJow3hM4SOLNs70pBB" %}
[Product Claims](/review/review-tool-concepts/document-review/feedback-cards/product-claims.md)
{% endcontent-ref %}

{% content-ref url="/pages/GstMKCAWDyjJT6SFPQCf" %}
[Trademarks](/review/review-tool-concepts/document-review/feedback-cards/trademarks.md)
{% endcontent-ref %}

{% content-ref url="/pages/oiQVzM4RBBcRgzRD7qgG" %}
[Policy Feedback](/review/review-tool-concepts/document-review/feedback-cards/policy-feedback.md)
{% endcontent-ref %}

For more info on how the Scans are done, see [Policy Engine](/review/review-tool-concepts/document-review/policy-engine.md).

**Text Highlighting:**

By default Protege will highlight the text in the doc that have a potential issue flagged in the Product Claims, Trademarks, and Policy Feedback cards. You can remove and reapply the highlighting at any time by pressing the button shown at the top of the nav bar.

![](/files/byV2UzrcovAvBi4Hx7Cz)

**Limitations**:

The extension has been tested for Protege AI up to 25 pages long and Google Slides up to 100 slides long. If you have content to review above those limits, please reach out to support to enable very long documents.


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.tryprotege.com/review/review-tool-concepts/document-review/conducting-reviews/office-365-word.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
