aiR Assist (Advanced Access)
aiR Assist application uses generative AI to help you investigate and better understand the data in your documents. You can use conversational language to ask the AI questions to save time locating relevant document information in Relativity. For example, you can ask it to find documents pertaining to specific people, keywords, or terms, such as ones around bribes or corruption. Then, you can identify key documents, understand communications and relationships between actors, and under actors and roles.
See these topics to start using aiR Assist:
- Best Practices
- Asking a question
- Navigating the Question box and Responses
- Using Index Manager
- Navigating Index Manager
Release notes
This section includes the release information and the current functionality of the aiR Assist (Advanced Access) application.
- New aiR Assist button—aiR Assist is available from the left sidebar instead of under the "Ask AI" button.
- New chat user interface—improved chat experience with the aiR Assist panel now opening on the left, while the Documents list is always in view on the right.
- Relocation of start a new chat—the start a new chat conversation option moved to the Answer a question box.
- New Index Manager—ability to filter Indexes and Data Sources (when creating an Index).
- Answer sharing—ability to copy answer to clipboard.
- Give Feedback—ability to rate an answer with Thumb Up or Thumb Down icons.
- Index rebuild—existing indexes can now be quickly updated to match changes in the saved search data source.
- Intent clarification—improves aiR Assist conversations by asking follow-up questions when your request is unclear, helping guide you to the right outcome and navigate the limitations.
- Saved Search Indexing—indexing documents from public saved searches is now supported.
- Multi-turn chat—simulates human conversation by preserving context from previous exchanges within the same chat session, which enables follow-up questions and deeper exploration without the need for repetition.
- Chat persistence—chat history is now saved and available for review even after user logs off their Relativity session.
- Start a new chat—this button starts a new chat conversation below the previous one, separated by a line. The new chat conversation does not reference previous conversations for its responses.
- Search Q&A button—the button is located on the top of the document list page and available for all users in the workspace to use.
- "Ask a question" box—when the panel is open, a user can input a natural language question about the documents. Each question is evaluated and answered individually without consideration of the full conversation.
- Workspace-level context—all indexed documents available in the workspace, up to 100,000, are subject to the querying process.
- Chat history—a user’s chat history is visible during that user’s Relativity session. Once the user logs out of Relativity the chat history will be cleared.
- Citations—references and citations are provided for each response. A user can filter the Document List to the show these references or can open each reference from the chat panel in the Document Viewer. Please note, that in the initial AA release, we do not confirm that the citations are grounded in the document text like in aiR for Review.
Considerations
Consider the following when using aiR Assist.
- aiR Assist supports:
- Up to 50,000 documents per index.
- Up to 5 MB of Extracted Text per document.
- There is no set limit on the number of questions you can ask in one session.
- Submitting the same question repeatedly can result in answers that vary, but they tend to be similar overall.
Conversation history remains available across user sessions and cannot be removed or cleared.
- A maximum of 25 references may be provided in response to a single inquiry.
- Multiple users can use aiR Assist in the same workspace and use the same indexes, but each user's session and chat history remain private and separate.
Currently, the system does not validate whether cited text is directly supported by the extracted content.
It primarily functions in English, and response quality may vary when processing documents in other languages.
It is not designed for calculations or numerical analysis.
Advanced intention recognition capabilities allows aiR Assist to decline questions outside its scope and seek clarification for those that are vague or overly broad.
Answers are generated using retrieval-augmented generation (RAG) techniques based on indexed data. Users are advised to independently verify all responses and citations for accuracy. Feedback is encouraged to support the continual enhancement of this resource.
Permissions
The aiR Assist application is accessible to users in workspaces that have aiR for Case Strategy installed, provided users have the necessary permissions listed below. Access to these workspaces is managed through standard workspace access permissions.
| Object Security |
|---|
|
For information on using aiR for Case Strategy, refer to
Data storage requirements
aiR Assist requires workspaces that are Data Grid File System (DGFS) enabled to function properly. Currently, it does not support environments where files are stored in SQL instead of Data Grid. Workspaces that rely on SQL-based file storage cannot be indexed or processed by aiR Assist.
aiR processing geography locations
When using Relativity's AI technology, the selected customer data may be processed outside of your specific Geo location as provided below. If not provided below, please contact your Relativity Success Manager for further information.
| RelativityOne Deployment Geography | aiR Processing Geography |
|---|---|
| APAC (Hong Kong, Japan, Singapore, South Korea) | Japan |
| Australia | Australia |
| Brazil | EU Data Boundary* |
| Canada | Canada |
| EEA (France, Germany, Ireland, Netherlands) | Germany |
| India | India |
| South Africa | EU Data Boundary* |
| Switzerland | Switzerland |
| United Kingdom | United Kingdom |
| United States | United States |
| United Arab Emirates | United Kingdom |
* See documentation on the Microsoft website for more information on the EU Data Boundary.
For more details about availability in your region, contact your account representative.
For technical specifications of your region's current LLM model, see documentation on the Azure website.
Accessing aiR Assist
To begin asking questions, click the aiR Assist (
) icon in the left nav bar.

Frequently asked questions
Listed are questions you might have using the aiR Assist application.
aiR Assist can handle questions related to the documents in the current workspace. Questions that answer general knowledge questions are not supported. You can ask questions in natural language, such as "Who are the key people in this case?" or "Which documents mention [topic]?"
There is no set limit, but long or highly complex queries may take more time to process. For best results, keep your questions concise and focused.
aiR Assist can return up to 25 references for one question, giving you a broad and well-supported set of sources.
Yes, it is private to you. At this time, each user's session and chat history remain private and separate and no one else can see it.
No. Your history persists between user sessions.
No. At this time, you cannot delete history.
Yes. aiR Assist uses advanced intention capabilities to reject questions that cannot be answered or are outside its scope, and it requests clarification for vague or overly broad queries.
aiR Assist primarily works in English. If your workspace contains documents in other languages, the effectiveness of answers may vary.
aiR Assist relies on indexed data to generate answers leveraging retrieval-augmented generation (RAG). While it aims to offer correct responses, always verify the offered information and citations for accuracy. Using the feedback buttons in the response box can help improve the tool over time.
Yes, multiple users can use aiR Assist within the same workspace concurrently. However, each user's session and chat history remain private and separate.