Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Launch Supplement

University of Alberta

$12,500.00

Towards Intelligent DevOps in the Era of Large-Language Models

FY 2024-25

Summary
The collaboration between teams is essential in modern software development, particularly in the context of DevOps. DevOps promotes a collaborative culture between developers and operators to continuously deliver new versions of software systems. As of 2023, the DevOps industry surpasses $14 billion and continues to expand. While major IT companies like Google, Netflix, and Amazon have already embraced DevOps practices, a significant portion of the industry still faces challenges in its adoption. Despite the popularity of DevOps, the collaboration aspect in DevOps has rarely been investigated and lacks actionable support for developers and operations teams. First, there is a lack of support for knowledge sharing. For example, operators often lack the development expertise needed to fully understand operational issues. Making the matter worse, the continuous development process in DevOps demands ongoing system evolution. Without support, developers and operators' views of the system may not align with how the system actually works. Another limitation is the lack of real-time collaboration between developers and operations. The need for collaboration is exacerbated in DevOps due to specialized roles, each with expertise in addressing specific issues. Besides, the readily-available operational data and development knowledge are rarely accessible or are provided in an ad hoc fashion. Such limitations often lead to misunderstandings and misalignment between developers and operators, which risks major issues like system crashes or security breaches due to poor communication. My long-term objective is to improve collaboration in DevOps practices to steer the software development process. I plan to focus on providing communicative agents for developers and operations teams to improve their knowledge sharing and involvement throughout the software lifecycle. The proposed research program is crucial due to the growing significance of DevOps in modern software development. With recent advancements in communicative agents, the program is well-timed and holds potential for substantial contributions to the software development and IT industry. My research will allow developers and operators to leverage LLM-powered communicative agents as a bridge between them to provide and validate solutions in issue reporting and debugging. Many Canadian software companies (e.g., CGI, Shopify, OpenText) have shown initiatives in DevOps practices. My research findings can provide a competitive edge in the $14 billion DevOps industry for both software practitioners like them and others in the field. This research program will train 10 Highly Qualified Personnel (HQP) in the field of Software Engineering: 2 PhD, 3 MSc students, and 5 undergraduate student researchers. Given the high demand for software developers in both industry and academia in Canada, the skills and expertise they will acquire through this research program will provide them with a competitive advantage.
Program
Discovery Launch Supplement
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
DGECR-2024-00207
Name nom
Chen, An Ran
Department département
Department of Electrical and Computer Engineering
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
12500
Program id
DGECR
Program name en
Discovery Launch Supplement
Program name fr
Supplément Tremplin vers la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2706
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Software engineering
Research subject fr
Génie logiciel
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Towards Intelligent DevOps in the Era of Large-Language Models
Keywords
devops; software debugging; software engineering; communicative agents; software quality; mining software repositories; program analysis; production issues
Application summary
The collaboration between teams is essential in modern software development, particularly in the context of DevOps. DevOps promotes a collaborative culture between developers and operators to continuously deliver new versions of software systems. As of 2023, the DevOps industry surpasses $14 billion and continues to expand. While major IT companies like Google, Netflix, and Amazon have already embraced DevOps practices, a significant portion of the industry still faces challenges in its adoption. Despite the popularity of DevOps, the collaboration aspect in DevOps has rarely been investigated and lacks actionable support for developers and operations teams. First, there is a lack of support for knowledge sharing. For example, operators often lack the development expertise needed to fully understand operational issues. Making the matter worse, the continuous development process in DevOps demands ongoing system evolution. Without support, developers and operators' views of the system may not align with how the system actually works. Another limitation is the lack of real-time collaboration between developers and operations. The need for collaboration is exacerbated in DevOps due to specialized roles, each with expertise in addressing specific issues. Besides, the readily-available operational data and development knowledge are rarely accessible or are provided in an ad hoc fashion. Such limitations often lead to misunderstandings and misalignment between developers and operators, which risks major issues like system crashes or security breaches due to poor communication. My long-term objective is to improve collaboration in DevOps practices to steer the software development process. I plan to focus on providing communicative agents for developers and operations teams to improve their knowledge sharing and involvement throughout the software lifecycle. The proposed research program is crucial due to the growing significance of DevOps in modern software development. With recent advancements in communicative agents, the program is well-timed and holds potential for substantial contributions to the software development and IT industry. My research will allow developers and operators to leverage LLM-powered communicative agents as a bridge between them to provide and validate solutions in issue reporting and debugging. Many Canadian software companies (e.g., CGI, Shopify, OpenText) have shown initiatives in DevOps practices. My research findings can provide a competitive edge in the $14 billion DevOps industry for both software practitioners like them and others in the field. This research program will train 10 Highly Qualified Personnel (HQP) in the field of Software Engineering: 2 PhD, 3 MSc students, and 5 undergraduate student researchers. Given the high demand for software developers in both industry and academia in Canada, the skills and expertise they will acquire through this research program will provide them with a competitive advantage.