AI App Generation from Free-Text Requirements and Auto Schemas
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building new applications from scratch is time-consuming and complex, especially for large enterprises with vast amounts of data and multiple permission sets, necessitating tools to aid users in creating apps with desired functionality.
Innovation Solution
An AI-driven user interface utilizing a large language model (LLM), embedding model, and heuristics to guide users through the app creation process, recommending components, generating schemas, and providing a preview for user modification, ultimately converting outputs into JSON primitives for app development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If users build applications from scratch using traditional methods, then they can create customized functionality, but the process becomes time-consuming and complex
Solution Approach 1:
The system performs preliminary actions by automatically generating application schemas, recommended components, and page structures based on user input descriptions before the user actually builds the application. The AI model pre-processes the requirements and prepares the foundational structure, so when the user reviews and approves, much of the groundwork is already done, significantly reducing the time required to create customized applications.
2Adaptability or versatility
If users build applications from scratch, then they can achieve desired functionality, but the process becomes complex and requires extensive manual work
Solution Approach 1:
The system enables self-service by allowing the AI to automatically generate application schemas, recommend components, and structure pages based on user input. The AI independently performs the complex tasks of analyzing requirements, selecting appropriate components, and organizing the application structure, reducing the manual complexity involved in building customized applications.
Solution Approach 2:
The AI model acts as an intermediary between the user's functional requirements and the actual application structure. Instead of users directly navigating complex development processes, they provide high-level descriptions to the AI, which then translates these into detailed schemas and component recommendations, simplifying the creation process while maintaining customization.
3Productivity
If AI generates application schemas and components automatically, then app creation efficiency improves, but the system complexity increases
Solution Approach 1:
The patent replaces manual mechanical processes of application design and schema creation with an AI-based intelligent system. Instead of users manually configuring each component and schema, the AI automatically generates these elements based on natural language input, significantly improving efficiency despite the increased system complexity.
Data Source
AI summary
A system receives a free text description of functionality desired for an application. The system creates first prompt including the free text description and a first request for a set of recommended components for the application. The system inputs the first prompt to a first generative language model and receives, as output, the set of recommended components for the application. The system generates a set of pages for at least a subset of the set of recommended components using a second generative language model. The system generates a schema for each page, where schema a defines a structure for storing data related to the respective page. The system determines a set of resources to include in each page. The system generates the application with the pages, the schemas, and the resources and provides access to the application to a client device.