aiR Assist

aiR Assist is a conversational search tool integrated within RelativityOne, designed to empower legal teams to interact with their data using natural language. By leveraging advanced AI, aiR Assist helps to surface potential insights, reveal possible connections, and uncover themes more efficiently. This can enhance the process they use to analyze and interpret legal data more effectively, potentially leading to quicker understanding, better decisions, and defensible workflows when validated by users.

It works by searching the extracted text of indexed documents. Users can create up to five indexes per workspace, each supporting up to 300,000 documents. When a query is submitted, aiR Assist identifies the documents deemed most relevant and employs a large language model (LLM) to generate answers with citations.

aiR Assist availability

aiR Assist is available to organizations with an aiR for Case Strategy contract or aiR Integrated contract. It does not require installation in RelativityOne.

Contract type	Availability
aiR for Case Strategy contract	aiR Assist is available in review workspaces where aiR for Case Strategy is installed and at least one Fact Extraction or Transcript Summary job has completed. Customers can also create a Case Home index. For more information about completing these jobs, refer to aiR for Case Strategy documentation. If an aiR for Case Strategy workspace does not meet the required conditions (aiR for Case Strategy is installed and a Fact Extraction or Transcript Summary job has completed), users can open aiR Assist, but they cannot use it until one of those jobs runs.
aiR Integrated contract	aiR Assist is available in both repository and review workspaces. The aiR for Case Strategy installation and job-completion requirements do not apply. Customers can also build a Case Home index based on aiR for Case Strategy documents. For more information about completing these jobs, refer to aiR for Case Strategy documentation.

To use aiR Assist, the appropriate permissions must be configured for each group in each workspace, regardless of contract type. See Permissions for more information. The aiR Assist icon appears at the top of the sidebar.

How aiR Assist works

aiR Assist operates using a Retrieval-Augmented Generation (RAG) process to deliver grounded, evidence-based responses. This approach combines document retrieval with large language model generation to help support accuracy, transparency, and contextual relevance.

1. Indexing the documents (indexing step)
   The user identifies documents to query and creates an index.
2. Asking a question (question step)
   The user asks a question.
   
3. Finding relevant documents (retrieval step)
   Each question is matched against the text indexed from the identified documents. aiR Assist performs a similarity search to identify the most relevant content. The documents are divided into smaller passages, and the system selects results that are estimated to correspond most closely to the question.
4. Generating the answer (generation step)
   The selected passages, along with the original question and system prompt, are passed to the LLM. The model uses this retrieved context to generate a response intended to be coherent, concise, and supported by retrieved content, citations, and references to the original sources.

Index and document limits

Below are the index and document limits.

Type	Limit
Index	Each index can contain up to 300,000 documents. A maximum of five (5) built indexes can be created per workspace. This can be from a combination of the Case Home document set (created in aiR for Case Strategy) and public saved searches.
Document	Individual documents must be up to 5 MB of extracted text; larger files are excluded during indexing. Only documents with extracted text are indexed. The text must be stored in Data Grid (not SQL). Files that do not contain extracted text are automatically excluded from the index.

Understanding aiR Assist responses

aiR Assist helps identify and summarize potentially relevant information across large document sets using natural language interaction. Built on a Retrieval-Augmented Generation (RAG) architecture, it retrieves and analyzes the documents most likely to be relevant, then generates a citation-supported response based on that content.

It returns contextually relevant and evidence-based information rather than performing exhaustive or “find everything” searches. Because it does not review each document individually, some keyword or topic matches may not be included in the response.

The RAG process works best when key evidence is found in a few focused documents. Results are less accurate if answers depend on scattered or unclear information.

Language support

The LLM used by aiR Assist has been evaluated for 83 languages. Although aiR Assist has primarily been tested on English-language documents, it is designed to support non-English datasets.

Unlike other aiR products, aiR Assist system consists of two components:

• Retrieval—the LLM generates search queries to find relevant documents in the index.
• Generation—the LLM summarizes the retrieved documents, picks relevant ones, and synthesizes them into an answer.

Because of this two-step design, there are special considerations when working with non-English datasets. If you use aiR Assist with non-English datasets, we recommend the following:

• When possible, write your question in the same language as the documents being queried—ideally your own native language. If that isn't possible, write your question in English.
• By default, aiR Assist searches for documents in English. If your documents are in another language and you are writing your question in English, tell it which language to search in by adding a sentence such as: "Search in <Language>." This helps the retrieval step generate queries in the specified language. While effective in most cases, the LLM may not always apply the requested language consistently.
• Extracted text and citations remain in the language of the source document — you do not need to translate them yourself before reviewing.
• By default, answers are generated in English. To request an answer in another language, add a sentence to your question, such as "Write answer in <Language>." This approach is effective in most cases, but the LLM may not always generate answer consistently in the requested language.

You can inspect which searches were attempted using the Search Completed summary in the response panel (see Navigating the responses). Use this to iterate on your question and adjust language coverage as needed.

Common use cases

Here are some example questions targeting a few common use cases for aiR Assist:

Use case	Common category	Example question
Early Case Insight	Finding potentially important documents	Can you find me documents that discuss potential gifts or incentives?
	Finding documents by theme	Are there any documents mentioning fraudulent behavior of John Doe?
	Understanding actors and roles	Who was involved in discussions about offering gifts?
Case Strategy Development	Identifying a series of events	Create a high-level timeline for events that took place before the start of Project Artemis.
	Understanding communications and relationships between actors	Who communicated with whom about the contract terms?
Deposition/Trial Preparation	Suggesting exhibits based on key criteria	List documents to use as exhibits based on [key document criteria].
	Confirming conversations or actions took place	Did John Maxwell send an email about the compliance policy?

Auditing user activity

You can monitor aiR Assist user activity in the Audit application in your Relativity instance. The Audit table records the events listed below. Because aiR Assist audit events are not RDO objects, they use an Audit Object UUID in the Audit table instead of an Object Artifact ID. For more information on using the Audit application, see Audit.

The following are aiR Assist object types and corresponding actions that will appear in the Audit table:

Object Type	Action
aiR Assist Question	Create—records auditing data when a question (prompt) was submitted from the Ask a question box. Audit does not record the content of the question.
aiR Assist Answer	Create—records auditing data when the answer to a question (prompt) was generated. Audit does not record the content of the answer.
aiR Assist Conversation	Create—records auditing data when a new question and answer conversation started (as in, when the user clicks the New conversation icon). Delete—records auditing data when the conversation was deleted. Edit—records auditing data when the conversation was edited (renamed). View—records auditing data when the conversation was opened for viewing from the Conversations panel.
aiR Assist Index	Create—records auditing data when the index was created. Delete—records auditing data when the index was deleted. Update—records auditing data when the index was updated (rebuilt).
aiR Assist Indexing Error List	View—records auditing data when the indexing error page was viewed.
aiR Assist Metadata Mapping	Update—records auditing data when the metadata mapping information was edited.

So, for example, if you opened a conversation, submitted a new question, and received an answer, the records would be as follows:

• aiR Assist Conversation = View
• aiR Assist Question = Create
• aiR Assist Answer = Create