# US 2025/0094474 A1 · Interface for agentic website search

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0094474 A1
- Document ID: US20250094474A1
- Status: Published application
- Kind: A1
- Application number: 18/967,625
- Filed: 2024-12-03
- Published: 2025-03-20
- Earliest claimed: 2022-12-16
- Assignees: C3.ai, Inc.
- Applicants: C3.ai, Inc.
- Inventors: Thomas M. Siebel; Nikhil Krishnan; Louis Poirier; Romain Juban; Michael Haines; Yushi Homma; Riyad Muradov
- Web page: https://patentgrep.com/patent/US20250094474A1

## CPC

- G06F 16/345: {Summarisation for human users}
- G06F 16/3326: {using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages}
- G06F 16/334: Query execution (filtering based on additional data G06F16/335)
- G06F 16/3347: {using vector based model}
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06F 16/338: Presentation of query results
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06N 3/045: Combinations of networks
- G06N 3/0475: Generative networks
- G06N 3/092: Reinforcement learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 3/063: using electronic means
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An agent-based website search interface utilizes a multimodal model to enhance enterprise operations. Data agents collect and process diverse inputs, while an orchestrator manages these agents. The system leverages machine learning models to generate insights and automate decision-making processes. It includes tools for data visualization and validation, ensuring accuracy and reliability. By integrating generative AI, the interface provides advanced search functionalities, improving user experience and operational efficiency. This facilitates seamless interaction to answer context specific questions from complex data, offering a robust solution for enterprise-level search and analysis.

## Claims

### Claim 1

A method for generating a response using a website search interface comprising:
receiving, via the search interface, one or more questions regarding content associated with the website;
processing the one or more questions by an orchestrator and multiple agents to generate the response to the one or more questions based on a corpus of information related to the website, wherein the orchestrator employs one or more multimodal models to process or deconstruct a prompt into a series of instructions for different agents;
displaying the response with one or more relevant sources from the corpus of information related to the website.

### Claim 2 (depends on 1)

The method of claim 1, wherein the multiple agents include a data validation agent, wherein the data validation agent determines the accuracy and reliability of the one or more relevant sources associated with the response.

### Claim 3 (depends on 1)

The method of claim 1, wherein displaying the response is presented using an intuitive non-complex human machine interface.

### Claim 4 (depends on 1)

The method of claim 1, wherein the multiple agents include a visualization agent, wherein the visualization generates a depiction of the one or more relevant sources associated with the response.

### Claim 5 (depends on 4)

The method of claim 4, wherein the depiction includes at least one of a link, a passage, a summarization, a data visualization, a graph, or an image.

### Claim 6 (depends on 1)

The method of claim 1,
wherein the multiple agents include a comprehension agent to generate a rationale for why it produced the response, and
wherein displaying the response further comprises providing the rationale with the response.

### Claim 7 (depends on 1)

The method of claim 1, wherein the corpus of information related to the website includes structured and unstructured data, and
wherein the multiple agents include different retrieval agents for structured and unstructured data.

### Claim 8 (depends on 1)

The method of claim 1, wherein the corpus of information related to the website includes a data model accessible using a model-driven architecture; and
wherein the multiple agents include a type system retriever agent of the model-driven architecture to retrieve a subset of the data model.

### Claim 9 (depends on 1)

The method of claim 1,
wherein the one or more questions includes a first question and a second question; and
further comprising processing the second question by the orchestrator, wherein a second response is generated based on the first question or a first response to the first question.

### Claim 10 (depends on 1)

The method of claim 1, further comprising collecting user feedback after displaying the response, wherein a feedback agent analyzes the user feedback to update the one or more multimodal models to refine accuracy and relevance of potential responses.

### Claim 11 (depends on 10)

The method of claim 10, wherein the feedback agent updates the corpus of information and improve the relevance of the potential responses.

### Claim 12 (depends on 1)

The method of claim 1, wherein the series of instructions for different agents includes an instruction to a utilize a computational tool to perform calculations on data from the corpus.

### Claim 13 (depends on 1)

The method of claim 1, wherein the series of instructions for different agents includes a task for processing text, images, or audio data optimized for the respective data type.

### Claim 14 (depends on 1)

The method of claim 1, wherein at least one instruction includes an API agent using an API tool to make calls to an application program interface.
