Focused View FAQs

Following Opus 2's acquisition of Uncover in October 2025, Opus 2 Cases and some of Uncover's AI technology have been integrated into the Opus 2 platform. As per the diagram shown below, there are now two views - Detailed View and Focused View. Detailed View is the existing Opus 2 Cases interface that you already know and all functionality you depend on is still available and unchanged. Focused View is a new, streamlined, AI-first, Uncover-inspired view where you can access the first capabilities arising from this integration.  You can seamlessly switch between the two views and documents surfaced by using Matter or Documents Assist in the Focused View can be added to collections or worksheets in the Detailed View.

If you have a question about the Focused View that doesn't appear here, please contact Opus 2 Platform Support.

FAQs on Functionality

1. Can I switch on the Focused View myself?

No, the Focused View must be enabled by Opus 2 Platform Support.

2. Can the Focused View be enabled/disabled for specific matters? 

Yes, Focused View can be enabled or disabled on a per-matter basis. If you need certain matters to have this functionality turned off, just let us know which ones during onboarding. Our implementation team will apply the appropriate feature flags and ensure those matters are configured correctly. 

Note: If you disable Focused View, all AI functionality is disabled.

3. Do I need to upload my case documents again before I can start using the new features?

No, after your firm has been introduced to Focused View and trained, all required documents in your Opus 2 Cases will be ready for use in the Focused View.

4. When uploading documents to Opus 2, the text in the documents is vectorised. What does vectorisation mean and why does Opus 2 use it? 

Vectorising text means turning words into numbers, called vectors, so that a computer can work with them. Computers don’t understand text the way humans do, but they do understand numbers. Those numbers represent the meaning of the text, not just the exact words. This means that the AI Assists can find relevant information in which the same idea is described in different words. In short, search results are more accurate and useful when combining keyword search with vector search.

5. Do users need to do anything for their documents to be vectorised? 

No, all documents in your Cases matters will be made available for use in the Focused View functionality. Your Account Manager and your firm's Point of Contact will align on the order in which your firm's Cases matters will be made available for use in the Focused View.  

After your firm has been introduced to Focused View, a script will vectorise new/changed documents every 10 minutes. The status column in the Documents Library and Select documents for AI Assist dialog shows the status of document vectorisation.

6. What do the numbers next to the cited source documents mean? 

The numbers that users see next to the cited source documents indicate the level of certainty that the piece of text from that document that was used to formulate the output was relevant.

7. What AI models are used by the Focused View?

The AI-driven functionality in Focused View was purpose built to use multiple large language models from various providers such as OpenAI and Anthropic. We constantly test new versions of LLMs as they are being released and may replace LLMs for newer versions when they outperform the current ones. Currently Focused View uses Anthropic's Claude 4.

8. What is the purpose of the thumbs up and thumbs down icons?

We encourage our users to indicate whether they are satisfied with the AI generated output by using the thumbs up and thumbs down buttons. By doing so Opus 2 are kept informed about the features’ performance and can act accordingly.  

9. Why don't I see citations in General Assist? 

The General Assist feature works differently as it does not use the documents uploaded to the case as input for formulating its answers but acts as a secure gateway to the entire database that the LLM draws from. 

10 . Are saved conversations user-specific or workspace-specific?

Saved conversations are user-specific and never deleted.

11. Are the prompt categories fixed or configurable?

The prompt categories are fixed. The user has the option to add their own prompts through the Prompt Builder. User made prompts are saved in My Prompts.

12. Can Matter Assist generate timelines without document limits?

Matter Assist is not built for making timelines. Timelines should be composed using the Timeline functionality in Documents Assist or through AI Workbench.

13. Is there an upper document limit when working with tools in the Focused View?

With thousands of documents, performance may suffer and you may run out of tokens in the Documents Assist LLM. When selecting documents using Matter Assist, there is a limit of 2000 documents. There is a limit of 150 pages when working in Documents Assist. 

14. How do permissions for viewing documents work in Focused View?

Permissions work as follows:

• If no users are allowed to view a document, the document does not enter the AI workflow and is not displayed anywhere.
• If a user is not allowed to view a document, it is unavailable for selection in the Source panel but is still listed. Citations are also greyed out and unavailable.
• AI responses may still include insights derived from restricted documents.

15. Why are Matter Assist and Document Assist being merged?

Customers reported confusion about when to use each assist.

Originally:

• Matter Assist analyzed information across the matter.
• Document Assist focused on select documents.

Later:

• Matter Assist gained the ability to analyze selected documents as well, making the distinction between the two less clear. As a result, users had to decide which assist was best for each query, creating unnecessary cognitive load. 

The unified experience removes that decision-making burden and allows the system to determine the best way to process the request. 

16. Will users still need to choose the right assist for their query?

No. The goal of the consolidation is to eliminate the need for users to determine which assist is most appropriate. 

The system uses backend routing logic to direct the query to the most suitable processing method, allowing users to simply ask their question and receive the best available answer. 

17. How should customers think about using the new unified assist?

Customers should simply ask their question and trust the system to determine the best processing approach. The goal is to provide the best answer available without requiring users to understand the underlying technology or maintain a list of use cases for different assists.

18. What are the key benefits of this change?

• Reduced user confusion. 
• Simplified experience with fewer assist options. 
• Less cognitive effort in selecting the correct tool. 
• Backend routing automatically determines the best processing method. 
• Faster adoption and improved usability. 
• Direct response to customer feedback.

The consolidation reflects customer feedback and demonstrates the team's commitment to simplifying the user experience and continuously improving the product. 

18. How does Matter Assist work now that Document Assist and Matter Assist have been combined?

Matter Assist is now designed to automatically select the most effective analysis method based on the content being reviewed. For smaller document sets, it may analyse the full text directly. For larger matters, it may use advanced retrieval techniques to identify and review the most relevant information.

This decision is made automatically behind the scenes, so users no longer need to choose between different AI workflows. Simply ask your question, and Matter Assist will use the most appropriate approach to generate a response.

19. Is there a document size limit?

Matter Assist can directly analyse document sets containing approximately 180,000 tokens (typically around 300-350 pages of legal text). For larger document collections, the system automatically uses retrieval techniques to analyse the most relevant content across the selected documents.

We continue to evaluate larger context windows as AI technology evolves and may increase these limits in the future. Any changes will be communicated through our release notes and product updates.

20. Does Matter Assist still use RAG?

Yes. Matter Assist uses a combination of direct content analysis, retrieval-based techniques, and agentic retrieval workflows. The system is designed to automatically determine the most appropriate approach based on the volume and characteristics of the selected content. This allows Matter Assist to work effectively across a wide range of content volumes without requiring users to choose a specific analysis mode. 

Related articles

About Focused and Detailed views

Using Focused view

Using AI Workbench to analyse documents