US-12626198-B2 - Systems and methods for using generative artificial intelligence with agile project management

US12626198B2US 12626198 B2US12626198 B2US 12626198B2US-12626198-B2

Abstract

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.

Inventors

Phillip J. Gollhofer
Dinesh A. Velhal

Assignees

BNSF RAILWAY COMPANY

Dates

Publication Date: 20260512
Application Date: 20240912

Claims (14)

1 . A system comprising: one or more memory units configured to store: a plurality of agile project management (APM) user stories, each APM user story of the plurality of APM user stories comprising a user description of a unit of work; a plurality of artificial intelligence (AI) chatbot prompts, wherein the plurality of AI chatbot prompts comprises: one or more instructions for an AI chatbot to assume a specific role; one or more instructions for the AI chatbot to give specific answers; and one or more instructions for the AI chatbot to give the specific answers in a specific format; and a plurality of large language model (LLM) parameters; one or more computer processors communicatively coupled to the one or more memory units and configured to execute machine-readable instructions, wherein the configuration of the one or more computer processors to execute the machine-readable instructions includes configuration to spawn more than one computer process concurrently, wherein the concurrent more than computer processes are configured to execute the machine-readable instructions to concurrently process data to perform program steps comprising: access an APM user story of the plurality of APM user stories; access the plurality of AI chatbot prompts and the plurality of LLM parameters, wherein the plurality of AI chatbot prompts instruct the AI chatbot to perform a rewrite of the APM user story; electronically transmit, to the AI chatbot across a communications network, the APM user story, the plurality of AI chatbot prompts, and the LLM parameters; electronically receive, 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; and display the APM AI response generated by the AI chatbot on an electronic display, wherein the APM AI response is a rewritten APM user story.
2 . The system of claim 1 , wherein: the plurality of AI chatbot prompts instruct the AI chatbot to perform a review of the APM user story; and the APM AI response is a review analysis that comprises: a plurality of suggestions for improving the APM user story; and a rating score that indicates a quality of the APM user story.
3 . The system of claim 1 , the one or more computer processors further configured to: electronically transmit, to the AI chatbot across the communications network, the rewritten APM story generated by the AI chatbot and additional AI chatbot prompts that instruct the AI chatbot to generate a second APM AI response, the second APM AI response comprising: a plurality of test cases for the rewritten APM story; a plurality of testing tips for the rewritten APM story; or acceptance criteria for the rewritten APM story; electronically receive, across the communications network, the second APM AI response generated by the AI chatbot using the rewritten APM story; and display the second APM AI response generated by the AI chatbot on the electronic display.
4 . The system of claim 1 , wherein the plurality of AI chatbot prompts further comprises one or more exclusion criteria for the AI chatbot.
5 . The system of claim 1 , wherein the plurality of LLM parameters comprises: a temperature setting that controls randomness when the AI chatbot chooses words during text creation; and a top_p setting that controls how many words the AI chatbot considers.
6 . A method by a computing system for using artificial intelligence (AI) with agile project management (APM), the method comprising: spawning more than one computer process concurrently, wherein the concurrent more than computer processes are configured to execute machine-readable instructions to concurrently process data to perform the steps of the method; accessing an APM user story of a plurality of APM user stories stored in one or more memory units, each APM user story of the plurality of APM user stories comprising a user description of a unit of work; accessing a plurality of artificial intelligence (AI) chatbot prompts stored in the one or more memory units, wherein the plurality of AI chatbot prompts comprises: one or more instructions for an AI chatbot to assume a specific role; one or more instructions for the AI chatbot to give specific answers; and one or more instructions for the AI chatbot to give the specific answers in a specific format; accessing a plurality of large language model (LLM) parameters stored in the one or more memory units, wherein the plurality of AI chatbot prompts instruct the AI chatbot to perform a rewrite of the APM user story; electronically transmitting, to the AI chatbot across a communications network, the APM user story, the plurality of AI chatbot prompts, and the LLM parameters; 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; and displaying the APM AI response generated by the AI chatbot on an electronic display, wherein the APM AI response is a rewritten APM user story.
7 . The method of claim 6 , wherein: the plurality of AI chatbot prompts instruct the AI chatbot to perform a review of the APM user story; and the APM AI response is a review analysis that comprises: a plurality of suggestions for improving the APM user story; and a rating score that indicates a quality of the APM user story.
8 . The method of claim 6 further comprising: electronically transmitting, to the AI chatbot across the communications network, the rewritten APM story generated by the AI chatbot and additional AI chatbot prompts that instruct the AI chatbot to generate a second APM AI response, the second APM AI response comprising: a plurality of test cases for the rewritten APM story; a plurality of testing tips for the rewritten APM story; or acceptance criteria for the rewritten APM story; electronically receiving, across the communications network, the second APM AI response generated by the AI chatbot using the rewritten APM story; and displaying the second APM AI response generated by the AI chatbot on the electronic display.
9 . The method of claim 6 , further comprising electronically transmitting, to a client system, an alert about the APM AI response generated by the AI chatbot.
10 . The method of claim 6 , wherein the plurality of LLM parameters comprises: a temperature setting that controls randomness when the AI chatbot chooses words during text creation; and a top_p setting that controls how many words the AI chatbot considers.
11 . One or more computer-readable non-transitory storage media embodying instructions that, when executed by a processor, cause the processor to perform operations comprising: spawning more than one computer process concurrently, wherein the concurrent more than computer processes are configured to execute machine-readable instructions to concurrently process data to perform the operations; accessing an APM user story of a plurality of APM user stories stored in one or more memory units, each APM user story of the plurality of APM user stories comprising a user description of a unit of work; accessing a plurality of artificial intelligence (AI) chatbot prompts stored in the one or more memory units, wherein the plurality of AI chatbot prompts comprises: one or more instructions for an AI chatbot to assume a specific role; one or more instructions for the AI chatbot to give specific answers; and one or more instructions for the AI chatbot to give the specific answers in a specific format; accessing a plurality of large language model (LLM) parameters stored in the one or more memory units, wherein the plurality of AI chatbot prompts instruct the AI chatbot to perform a rewrite of the APM user story; electronically transmitting, to the AI chatbot across a communications network, the APM user story, the plurality of AI chatbot prompts, and the LLM parameters; 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; and displaying the APM AI response generated by the AI chatbot on an electronic display, wherein the APM AI response is a rewritten APM user story.
12 . The one or more computer-readable non-transitory storage media of claim 11 , wherein: the plurality of AI chatbot prompts instruct the AI chatbot to perform a review of the APM user story; and the APM AI response is a review analysis that comprises: a plurality of suggestions for improving the APM user story; and a rating score that indicates a quality of the APM user story.
13 . The one or more computer-readable non-transitory storage media of claim 11 , the operations further comprising: electronically transmitting, to the AI chatbot across the communications network, the rewritten APM story generated by the AI chatbot and additional AI chatbot prompts that instruct the AI chatbot to generate a second APM AI response, the second APM AI response comprising: a plurality of test cases for the rewritten APM story; a plurality of testing tips for the rewritten APM story; or acceptance criteria for the rewritten APM story; electronically receiving, across the communications network, the second APM AI response generated by the AI chatbot using the rewritten APM story; and displaying the second APM AI response generated by the AI chatbot on the electronic display.
14 . The one or more computer-readable non-transitory storage media of claim 11 , wherein the plurality of LLM parameters comprises: a temperature setting that controls randomness when the AI chatbot chooses words during text creation; and a top_p setting that controls how many words the AI chatbot considers.

Description

TECHNICAL FIELD This disclosure generally relates to agile project management (APM), and more specifically to systems and methods for using generative artificial intelligence (AI) with APM. BACKGROUND Agile project management (APM) is an iterative approach to managing software development projects. APM involves continuous releases while soliciting and incorporating feedback from customers with every iteration. A typical APM process begins with a user creating a user story that includes a description of a unit of work (e.g., software to accomplish a specific task). The user story is then collectively reviewed and refined by a team that includes the product owner, a developer, and a quality tester. However, user stories that are manually created by users are often incomplete, lack a uniform format, and are inefficient at conveying the desired unit of work to be performed. SUMMARY The present disclosure achieves technical advantages as systems, methods, and computer-readable storage media for using artificial intelligence (AI) with agile project management (APM). The present disclosure provides for a system integrated into a practical application with meaningful limitations that may include electronically transmitting, to an AI chatbot across a communications network, an APM user story, a plurality of AI chatbot prompts, and a plurality of LLM parameters. Other meaningful limitations of the system integrated into a practical application include: 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; and displaying the APM AI response generated by the AI chatbot on an electronic display. The present disclosure solves the technological problem of a lack of technical functionality for automatically generating APM user stories. The technological solutions provided herein, and missing from conventional systems, are more than a mere application of a manual process to a computerized environment, but rather include functionality (including artificial intelligence functionality) to implement a technical process to supplement current manual solutions for generating APM user stories. In doing so, the present disclosure goes well beyond a mere application the manual process to a computer. Unlike existing solutions where personnel may be required to manually generate APM user stories, embodiments of this disclosure provide systems and methods that provide functionality for utilizing AI to analyze and rewrite APM user stories. By providing AI-generated user stories in an APM environment, the efficiency of the APM environment may be increased and bandwidth of personnel typically tasked with reviewing and revising APM user stories may be increased. For example, the time required to analyze and revise APM user stories may be greatly reduced. Furthermore, AI-generated APM user stories of the disclosed embodiments may enable better iterations of software code, thereby reducing computing resources (e.g., processing, memory, and electrical power) that would otherwise be used with poorly-written APM user stories. Other technical advantages will be readily apparent to one skilled in the art from the following figures, descriptions, and claims. Moreover, while specific advantages have been enumerated above, various embodiments may include all, some, or none of the enumerated advantages. In some embodiments, the disclosed models are formulated or otherwise configured to utilize various constraints and objectives in order to perform or execute a designated task (e.g., one or more features of APM AI tool 160, in accordance with one or more embodiments of the present disclosure). In other embodiments, the present disclosure includes techniques for implementing and training models (e.g., machine-learning models, artificial intelligence models, algorithmic constructs, optimizers, etc.) for performing or executing a designated task or a series of tasks (e.g., one or more features of APM AI tool 160, in accordance with one or more embodiments of the present disclosure). In these embodiments, the disclosed techniques provide a systematic approach for the training of such models to enhance performance, accuracy, and efficiency in their respective applications. In embodiments, the techniques for training the models can include collecting a set of data from a database, conditioning the set of data to generate a set of conditioned data, and/or generating a set of training data including the collected set of data and/or the conditioned set of data. In some embodiments, a model can undergo a training phase wherein the model may be exposed to the set of training data, such as through an iterative processes of learning in which the model adjusts and optimizes its parameters and algorithms to improve its performance on the designated task or series of tasks. This training phase may configure the model to develop t