Connected AI Agent Routing for Enterprise Message Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing large language models (LLMs) are limited in responding to questions involving personal and enterprise content items due to training on non-inclusive data sources, and users face difficulties in locating relevant information within messaging applications, leading to inefficient and distracting search processes.
Innovation Solution
A connected AI agent system that integrates a connector service and AI agent across servers, vectorizes user content, and executes agent objects to provide intelligent responses within messaging environments, leveraging user permissions and management policies to access and generate relevant content chunks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If users perform traditional text searching in folders or message histories, then they can locate relevant personal and enterprise items, but the process is time-consuming and requires leaving the messaging environment
Solution Approach 1:
The patent introduces an AI agent as an intermediary between the user and the content repositories. The AI agent receives natural language queries from users within the messaging application and automatically searches across multiple content sources (email, documents, calendars, etc.), returning results without requiring users to leave the messaging interface or manually search through folders.
Solution Approach 2:
The AI agent is designed to perform multiple functions: it can search across different content types (email, documents, calendars), understand natural language queries, and return contextualized results. This multi-functional approach eliminates the need for separate search tools and manual folder navigation, significantly reducing search time while maintaining ease of use.
2Loss of information
If public LLMs are used to answer questions, then they can provide general knowledge responses, but they cannot access personal and enterprise content items
Solution Approach 1:
The patent implements a nested architecture where the AI agent is embedded within the enterprise messaging system. The AI agent contains embedded components including an embedding model for vectorization, access to enterprise content repositories, and integration with the messaging application. This nested structure allows the AI agent to leverage both the general capabilities of LLMs and the specific access to enterprise content, enabling it to answer questions that require both general knowledge and organization-specific information.
3Adaptability or versatility
If users open multiple applications for searching, then they can access different content sources, but resources and user attention are competed for
Solution Approach 1:
The patent merges multiple content access capabilities into a single AI agent interface. Instead of requiring users to open separate applications for email, documents, calendars, and other content sources, the AI agent consolidates access to all these repositories through one unified interface within the messaging application. This reduces resource consumption by eliminating redundant application instances and reduces user attention demands by providing a single point of access.
Data Source
AI summary
Systems and methods are described for a connected AI agent for managed multidimensional search based on an electronic message and management policies. A messaging application at a client device can send a new electronic message, such as an email, to a connector service. An attachment can be ingested and stored in a vector database. Then one or more artificial intelligence (“AI”) agents can be selected for responding to the body of the email, such as a query in the body. The responses can be formatted and sent to multiple parties, such as a sending user of the electronic message and a recipient that was copied or also sent the new electronic message. The AI agents can use different AI models, prompts, and vector databases depending on user permissions. This allows for building up vector databases with relevant content items and answering user questions based on those vector databases.