Generative Engine Child Issue Creation from Parent Issues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing issue tracking systems struggle to efficiently generate detailed subtasks from parent issues due to the complexity and diversity of multi-platform environments, leading to inefficiencies, delays, and inaccuracies in project management.
Innovation Solution
A method using a large language model to generate subtasks by leveraging context from multiple software platforms, including issue tracking, content collaboration, and project management platforms, through an iterative process to ensure detailed and accurate subtask creation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual task breakdown is used to create detailed subtasks from parent issues, then task accuracy and completeness can be ensured, but time consumption and productivity are reduced
Solution Approach 1:
The patent introduces an AI assistant as an intermediary between the parent issue and the final subtasks. The AI assistant retrieves relevant context from multiple software platforms (content collaboration platforms, issue tracking platforms, project management platforms) and uses this context to generate accurate subtasks, thereby maintaining precision while improving productivity.
Solution Approach 2:
The system performs preliminary actions by proactively retrieving and preparing context information from various platforms before the user requests subtask generation. The AI assistant pre-processes available resources (documents, issues, project details) so that when subtasks need to be created, the relevant information is already gathered and ready, reducing the overall time required.
2Reliability
If context from multiple software platforms is manually gathered to inform subtask creation, then subtask completeness and resource leverage are improved, but system complexity and operational difficulty increase
Solution Approach 1:
The patent creates a universal system that can retrieve context from multiple different software platforms through a unified interface. The AI assistant is designed to work with various platform types (content collaboration, issue tracking, project management) using common patterns and protocols, allowing it to leverage resources across platforms without requiring separate manual integration processes for each platform.
Solution Approach 2:
The AI assistant performs self-service by autonomously navigating multiple platforms, identifying relevant context, and retrieving necessary information without human intervention. The system automatically determines what resources are needed from each platform and gathers them independently, reducing the operational complexity for users.
3Productivity
If AI-generated subtasks are created without iterative refinement, then generation speed is improved, but task accuracy and completeness may be compromised
Solution Approach 1:
The patent implements a feedback mechanism where the AI assistant generates initial subtasks, receives user feedback on their quality and completeness, and then refines them iteratively. The system learns from user corrections and adjustments, continuously improving subtask quality while maintaining efficient generation speeds through the feedback loop.
Data Source
AI summary
Systems and methods described herein are configured to generate a set of child issues based on a parent issue. A system may be configured to obtain information from the parent issue and get resource identifiers to traverse a content node graph. The content node graph may provide other resource identifiers related to the initial resource identifier, which can, in turn, be used to fetch content from the system. The content is used to provide context beyond the parent issue. The parent issue, the context, and other predetermined formats and queries are used to generate a prompt that is submitted to a generative output engine. Based on the output from the generative engine, the system decides if more context is needed and/or extracts suggested subtasks from the output. The suggested subtasks may be used to cause child issues to be generated in the issue tracking platform.