AI Workflow Tool for Testable Software Requirements and QA

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing software development tools often prioritize speed over quality and reliability, leading to increased technical debt, project cost overruns, and unmet project goals, while lacking versatility in generating comprehensive development assets.

Innovation Solution

GILES, a software development tool leveraging Generative AI, integrates Agile and Behavior-Driven Design principles to generate testable requirements, test cases, and documentation, emphasizing rigorous testing and customized prompting to ensure high-quality outputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional software development processes are followed to ensure quality and reliability, then software quality and reliability are improved, but development time and cost increase

Engineering Contradiction:
Improvesoftware qualityVSAvoiddevelopment time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service through automated AI agents that independently perform software development tasks including code generation, testing, and documentation. The autonomous agents navigate the development workflow without constant human intervention, automatically completing steps such as generating test cases from requirements and creating documentation from code, thereby maintaining quality while reducing development time.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by pre-generating test cases from requirements during the planning phase, and pre-creating documentation templates before actual development. This preliminary preparation ensures quality requirements are built-in from the start rather than added later, reducing rework and accelerating the overall development process.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If comprehensive development assets are generated to ensure project goals are met, then project completeness is improved, but computing resource utilization increases

Engineering Contradiction:
Improvedevelopment asset completenessVSAvoidcomputing resource utilization
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system segments the development process into distinct phases (requirements, design, implementation, testing, documentation) with specialized AI agents for each phase. Each agent generates only the specific assets needed for its phase rather than all assets simultaneously, reducing peak computing resource utilization while ensuring comprehensive coverage across all development aspects.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements partial action by generating development assets incrementally and on-demand rather than all at once. Test cases are generated when needed for specific features, documentation is created as code is completed, allowing the system to manage computing resources efficiently while still producing comprehensive development assets throughout the project lifecycle.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4654004A1Software development tool and method for using the same
Publication Date: 2025.11.26 CONCENTRIX CVG CUSTOMER MANAGEMENT DELAWARE LLC
  • EP4654004A1 patent drawingFigure 1A
  • EP4654004A1 patent drawingFigure 1B
  • EP4654004A1 patent drawingFigure 1C

AI summary

Systems and methods for software development tool and use thereof. The method can include accessing input data including a config file. The method can include processing the config file to generate output including (i) phases of a workflow and (ii) steps for the respective phases of the workflow. The method can include initiating a chat session for a step. The chat session including a conversation between a user and a first machine-learned model to work on the step. The method can include determining that the step has been completed and extracting output including conversation context data. The method can include determining that all phases of the workflow are complete. The method can include generating, based on the output and the conversation context data, output including an executable plan indicative of the one or more steps and the one or more phases.