Connected AI Agents for Permission-Based 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 environments, especially on mobile devices with limited screen space.
Innovation Solution
A connected AI agent system that integrates a connector service and AI agent across servers, vectorizes user content items, and executes agent objects to provide personalized responses within messaging applications, leveraging user permissions and management policies to access and respond to queries using vector databases and AI models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If public LLMs are used to answer questions, then general knowledge responses are provided, but they cannot access personal and enterprise content items
Solution Approach 1:
The patent introduces an AI agent as an intermediary component that bridges public LLMs and personal/enterprise content items. The AI agent retrieves relevant personal content from storage systems and passes it to the LLM, enabling the LLM to answer questions about personal content without directly accessing it. This mediator approach resolves the contradiction by allowing general knowledge models to provide reliable responses about personal content through indirect access.
2Measurement precision
If users perform text searching in folders or message histories, then they can locate relevant information, but it is time consuming and difficult
Solution Approach 1:
The patent replaces manual text searching mechanics with AI-powered semantic search. Instead of users manually filtering through folders and messages, the AI agent understands the query intent, retrieves relevant personal content items using semantic matching, and presents results. This substitution of mechanical searching with intelligent retrieval dramatically reduces time while improving accuracy.
3Quantity of substance
If users leave the messaging environment to perform searches, then they can access more information, but they are distracted and must manage multiple applications
Solution Approach 1:
The patent merges the search functionality directly into the messaging environment by deploying an AI agent within the chat interface. Users can query personal content items without leaving the messaging application, as the AI agent processes queries and returns results in-context. This integration combines information retrieval and communication functions, maintaining user focus while expanding information accessibility.
4Weight of moving object
If mobile devices are used for messaging, then portability is improved, but screen space is limited making searches more difficult
Solution Approach 1:
The patent extracts the complex search and information retrieval processing from the mobile device itself and relocates it to a cloud-based AI agent. The mobile device only needs to display concise queries and results, while the heavy lifting of searching through personal content items occurs remotely. This extraction allows portable devices with limited screens to access extensive information without requiring large display areas.
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.