# US 2026/0087571 A1 · Artificial intelligence (ai)-based legal assistant > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0087571 A1 - Document ID: US20260087571A1 - Status: Published application - Kind: A1 - Application number: 19/072,415 - Filed: 2025-03-06 - Published: 2026-03-26 - Earliest claimed: 2024-09-25 - Assignees: Querious, Inc. - Applicants: Querious, Inc. - Inventors: Eugene De Villiers; Hilary Bowman; Anthony Dey - Web page: https://patentgrep.com/patent/US20260087571A1 ## CPC - G06Q 50/18: Legal services - G06F 40/30: Semantic analysis - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A computer-based legal assistant tool is operable to receive information regarding a client, including legal documents, audio data from a meeting or a transcript therefrom, or other contextual information. The tool utilizes artificial intelligence to automatically generate at least one suggestion via a natural language output using a large language model. The at least one suggestion is based on training data used to train the artificial intelligence via at least one database to identify laws matching the information regarding the client. The at least one suggestion includes at least one question, relevant legal content, and/or a collaborator for an attorney that are relevant to the legal issues at hand. The tool is operable to automatically generate a summary of a meeting, the summary including follow-up items to provide to an attorney. ## Claims ### Claim 1 An artificial intelligence (AI)-based system for automatically suggesting potential legal issues, comprising: at least one computer processor including a memory; at least one AI engine; and at least one user account; wherein the at least one user account hosts and/or attends at least one virtual meeting; wherein the at least one AI engine is integrated into a video chat interface; wherein the at least one computer processor is operable to receive at least one input from the at least one user account; wherein the at least one input includes a live conversation; wherein the at least one input is not uploaded information; wherein the at least one AI engine is operable to automatically determine at least one suggestion, in real-time, during the at least one virtual meeting based on the at least one input; wherein the at least one AI engine is operable to generate a standalone browser window separate from the video chat interface; wherein the standalone browser window and the video chat interface are displayed via a graphical user interface (GUI); wherein the at least one AI engine utilizes at least one application programming interface (API) to automatically resize and/or reorganize icons on the video chat interface after generating the standalone browser window such that the video chat interface and the standalone browser window are simultaneously displayed via the GUI; wherein the at least one suggestion includes at least one question, at least one legal issue automatically identified by the at least one AI engine, relevant legal content relating to the at least one legal issue, and/or at least one collaborator; and wherein the at least one AI engine is operable to populate the standalone browser window with the at least one suggestion based on the at least one input to display to the at least one user account. ### Claim 2 (depends on 1) The system of claim 1, wherein the at least one AI engine is operable to utilize natural language processing to process the at least one input, and wherein the at least one input includes audio transcripts, live audio data, text, and/or at least one document. ### Claim 3 (depends on 1) The system of claim 1, wherein the at least one AI engine is operable to determine a relevant jurisdiction for the at least one legal question based in part on geolocation, input received from the plurality of user accounts, at least one administrative account, and/or natural language processing (NLP). ### Claim 4 (depends on 1) The system of claim 1, wherein the at least one AI engine is operable to generate at least one structured summary organized by topic based on context from the at least one virtual meeting. ### Claim 5 (depends on 4) The system of claim 4, wherein the at least one AI engine is operable to generate additional structured summaries for subsequent meetings, and wherein the at least one AI engine is operable to aggregate and summarize a combination of the at least one structured summary and the additional structured summaries. ### Claim 6 (depends on 1) The system of claim 1, wherein the at least one AI engine is operable to determine the at least one suggestion by ingesting and training from scraped web data, utilizing a search engine, and/or searching at least one database and outputting the at least one suggestion as a natural language output via a large language model. ### Claim 7 (depends on 1) The system of claim 1, wherein the AI-based system is operable to integrate with at least one video conferencing platform. ### Claim 8 An artificial intelligence (AI)-based system for automatically suggesting potential legal issues, comprising: at least one computer processor including a memory; at least one AI engine including a large language model; and at least one user account; wherein the at least one user account hosts and/or attends at least one virtual meeting; wherein the at least one AI engine is integrated into a scheduling platform via at least one application programming interface (API); wherein the at least one AI engine creates pre-meeting context for the at least one virtual meeting before the at least one virtual meeting based in part on data extracted from the scheduling platform; wherein the at least one computer processor is operable to receive at least one input from the at least one user account; wherein the at least one input includes a live conversation; wherein the at least one input is not uploaded information; wherein the at least one AI engine creates in-meeting context for the at least one virtual meeting in real-time based on the at least one input; wherein the at least one AI engine is operable to utilize natural language processing to analyze the at least one input; wherein the at least one AI engine is operable to automatically determine at least one suggestion, in real-time, during the at least one virtual meeting based on the at least one input; wherein the at least one AI engine utilizes the in-meeting context to fine tune, in real-time, the at least one suggestion to increase relevancy of the at least one suggestion to the at least one user account; wherein the at least one suggestion includes at least one question, at least one legal issue automatically identified by the at least one AI engine, relevant legal content relating to the at least one legal issue, and/or at least one collaborator; and wherein the at least one suggestion is displayed to the at least one user account as a natural language output via the large language model. ### Claim 9 (depends on 8) The system of claim 8, wherein the at least one AI engine is operable to generate at least one structured summary organized by topic based on context from the at least one virtual meeting. ### Claim 10 (depends on 8) The system of claim 8, wherein the at least one AI engine is operable to determine the at least one legal issue by querying at least one legal database, scraping data from at least one publicly available internet source, conducting a semantic analysis of the at least one input, and/or by the at least one AI engine analyzing at least one document. ### Claim 11 (depends on 8) The system of claim 8, wherein the AI-based system is operable to integrate with at least one video conferencing platform. ### Claim 12 (depends on 8) The system of claim 8, wherein the at least one collaborator includes a qualified professional based on the at least one legal issue. ### Claim 13 (depends on 8) The system of claim 8, wherein the at least one question includes a solicitation for more information about the at least one legal issue. ### Claim 14 (depends on 8) The system of claim 8, wherein the at least one AI engine is operable to determine a relevant jurisdiction based in part on geolocation, input received from the plurality of user accounts, a document, and/or natural language processing (NLP). ### Claim 15 (depends on 8) The system of claim 8, wherein the at least one input is operable to include text, audio, video, and/or at least one document. ### Claim 16 (depends on 8) The system of claim 8, wherein the relevant legal content includes information from relevant statutes, regulations, laws, and/or any other relevant legal source, and wherein the at least one AI engine includes citations to the relevant legal content within the at least one suggestion. ### Claim 17 An artificial intelligence (AI)-based system for automatically suggesting potential legal issues, comprising: at least one computer processor including a memory; at least one AI engine; and at least one user account; wherein the at least one user account hosts and/or attends at least one virtual meeting; wherein the at least one AI engine is integrated into a video chat interface; wherein the at least one AI engine is integrated into a scheduling platform via a first set of at least one application programming interface (API); wherein the at least one AI engine creates pre-meeting context for the at least one virtual meeting before the at least one virtual meeting based in part on data extracted from the scheduling platform; wherein the at least one computer processor is operable to receive at least one input from the at least one user account; wherein the at least one input includes a live conversation; wherein the at least one input is not uploaded information; wherein the at least one AI engine creates in-meeting context for the at least one virtual meeting in real-time based on the at least one input; wherein the at least one AI engine is operable to automatically determine at least one suggestion, in real-time, during the at least one virtual meeting based on the at least one input; wherein the at least one AI engine utilizes the in-meeting context to fine tune, in real-time, the at least one suggestion to increase relevancy of the at least one suggestion to the at least one user account; wherein the at least one suggestion includes at least one question, at least one legal issue automatically identified by the at least one AI engine, relevant legal content relating to the at least one legal issue, and/or at least one collaborator; wherein the at least one AI engine is operable to generate a standalone browser window separate from the video chat interface and/or generate a chat browser integrated into the video chat interface; wherein the standalone browser window and/or the chat browser and the video chat interface are displayed via a graphical user interface (GUI); wherein the at least one AI engine utilizes a second set of at least one API to automatically resize and/or reorganize icons on the video chat interface after generating the standalone browser window and/or the chat browser such that the video chat interface and the standalone browser window and/or the chat browser are simultaneously displayed via the GUI; wherein the at least one AI engine is operable to populate the standalone browser window and/or the chat browser with the at least one suggestion based on the at least one input to display to the at least one user account; and wherein the at least one AI engine is operable to generate a structured summary of the at least one virtual meeting organized by topics discussed in the at least one virtual meeting. ### Claim 18 (depends on 17) The system of claim 17, wherein the at least one AI engine is operable to generate additional structured summaries for subsequent meetings, and wherein the at least one AI engine is operable to aggregate and summarize a combination of the structured summary and the additional structured summaries to use as context for future meetings. ### Claim 19 (depends on 18) The system of claim 18, wherein the at least one AI engine is operable to use the structured summary, the additional structured summaries, and/or the combination of the structured summary and the additional structured summaries to recommend at least one professional. ### Claim 20 (depends on 17) The system of claim 17, wherein the at least one AI engine is operable to modify the structured summary based in part on information saved in the memory for a particular client.