AI Chatbot Refinement of Agile User Stories for Testing Coverage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manually created APM user stories are often incomplete, lack a uniform format, and are inefficient at conveying the desired unit of work, leading to inefficiencies in the review and refinement process by the three amigos, resulting in testing gaps and elevated risks of failure.
Innovation Solution
Utilizing generative AI to review and refine APM user stories by integrating an AI chatbot that analyzes and rewrites user stories using AI chatbot prompts and LLM parameters, generating standardized and detailed responses that can be displayed for further review.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user stories are manually created by users, then the APM process can proceed with initial user stories, but the user stories are often incomplete, lack uniform format, and are inefficient at conveying the desired unit of work
Solution Approach 1:
An AI assistant is introduced as an intermediary between the user and the APM system. The user provides initial user story ideas, and the AI assistant automatically generates complete, standardized user stories with all required fields (title, description, acceptance criteria, etc.), eliminating the need for users to manually create complete and formatted user stories while ensuring high quality and consistency.
Solution Approach 2:
The AI assistant performs preliminary actions by automatically generating complete user stories, acceptance criteria, and test cases before the actual APM review process begins. This preliminary generation of comprehensive documentation ensures that all necessary information is prepared in advance with proper formatting, reducing the need for later revisions and manual completion.
2Reliability
If user stories are manually reviewed and refined by the three amigos, then feedback can be incorporated, but the process is time-consuming and results in testing gaps and elevated risks of failure
Solution Approach 1:
The AI assistant operates continuously to generate user stories, acceptance criteria, and test cases without interruption. Unlike manual review processes that require coordination between multiple team members over time, the AI system continuously generates and refines documentation, ensuring that all necessary artifacts are always available and up-to-date, thereby eliminating delays and testing gaps.
Solution Approach 2:
The system enables self-service by automatically generating complete user stories with all required fields and test cases without requiring manual review and refinement by the three amigos. The AI assistant independently produces high-quality, standardized documentation that is ready for immediate use, significantly reducing the time investment required from team members while maintaining or improving quality.
3Productivity
If AI is used to generate user stories, then efficiency of the APM environment is increased and bandwidth of personnel is increased, but additional AI infrastructure and integration are required
Solution Approach 1:
The AI assistant is designed as a universal tool that can generate multiple types of APM artifacts (user stories, acceptance criteria, test cases, task breakdowns) from a single interface. This multi-functionality consolidates what would otherwise require multiple separate tools and integration points into one unified system, reducing overall system complexity while maximizing productivity gains across the entire APM workflow.
Data Source
AI summary
A method for using artificial intelligence (AI) with agile project management (APM) includes accessing an APM user story, a plurality of an AI chatbot prompts, and a plurality of large language model (LLM) parameters. The APM user story includes a user description of a unit of work. The method further includes electronically transmitting, to an AI chatbot across a communications network, the APM user story, the plurality of AI chatbot prompts, and the LLM parameters. The method further includes electronically receiving, across the communications network, an APM AI response generated by the AI chatbot using the APM user story, the plurality of AI chatbot prompts, and the LLM parameters. The method further includes displaying the APM AI response generated by the AI chatbot on an electronic display.