Maja Vukovic
Research Subjects
Maja Vukovic has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
- Anup K. Kalia
IBM Research USA
2 shared publications - Jin Xiao
IBM Research USA
2 shared publications Rahul Krishna
2 shared publications- A. K. Kalia
IBM Res, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
1 shared publication - A. Mahamuni
IBM Global Technol Serv GTS, Bangalore 560045, Karnataka, India
1 shared publication A. Natarajan
1 shared publication
Latest Publications
- Open Access
Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study
The rise of large language models (LLMs) has accelerated the development of automated techniques and tools for supporting various software engineering tasks, e.g., program understanding, code generation, software testing, and program repair. As CodeLLMs are being employed toward automating these tasks, one question that arises, especially in enterprise settings, is whether these coding assistants and the code LLMs that power them are ready for real-world projects and enterprise use cases, and how do they impact the existing software engineering process and user experience. In this paper we survey 57 developers from different domains and with varying software engineering skill about their experience with AI coding assistants and CodeLLMs. We also reviewed 35 user surveys on the usage, experience and expectations of professionals and students using AI coding assistants and CodeLLMs. Based on our study findings and analysis of existing surveys, we discuss the requirements for AI-powered coding assistants.
Open AccessUsage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study
The rise of large language models (LLMs) has accelerated the development of automated techniques and tools for supporting various software engineering tasks, e.g., program understanding, code generation, software testing, and program repair. As CodeLLMs are being employed toward automating these tasks, one question that arises, especially in enterprise settings, is whether these coding assistants and the code LLMs that power them are ready for real-world projects and enterprise use cases, and how do they impact the existing software engineering process and user experience. In this paper we survey 57 developers from different domains and with varying software engineering skill about their experience with AI coding assistants and CodeLLMs. We also reviewed 35 user surveys on the usage, experience and expectations of professionals and students using AI coding assistants and CodeLLMs. Based on our study findings and analysis of existing surveys, we discuss the requirements for AI-powered coding assistants.
- Open Access
An Expert System for Redesigning Software for Cloud Applications
Cloud-based software has many advantages. When services are divided into many independent components, they are easier to update. Also, during peak demand, it is easier to scale cloud services (just hire more CPUs). Hence, many organizations are partitioning their monolithic enterprise applications into cloud-based microservices. Recently there has been much work using machine learning to simplify this partitioning task. Despite much research, no single partitioning method can be recommended as generally useful. More specifically, those prior solutions are "brittle"; i.e. if they work well for one kind of goal in one dataset, then they can be sub-optimal if applied to many datasets and multiple goals. In order to find a generally useful partitioning method, we propose DEEPLY. This new algorithm extends the CO-GCN deep learning partition generator with (a) a novel loss function and (b) some hyper-parameter optimization. As shown by our experiments, DEEPLY generally outperforms prior work (including CO-GCN, and others) across multiple datasets and goals. To the best of our knowledge, this is the first report in SE of such stable hyper-parameter optimization. To aid reuse of this work, DEEPLY is available on-line at https://bit.ly/2WhfFlB.
Open AccessAn Expert System for Redesigning Software for Cloud Applications
Cloud-based software has many advantages. When services are divided into many independent components, they are easier to update. Also, during peak demand, it is easier to scale cloud services (just hire more CPUs). Hence, many organizations are partitioning their monolithic enterprise applications into cloud-based microservices. Recently there has been much work using machine learning to simplify this partitioning task. Despite much research, no single partitioning method can be recommended as generally useful. More specifically, those prior solutions are "brittle"; i.e. if they work well for one kind of goal in one dataset, then they can be sub-optimal if applied to many datasets and multiple goals. In order to find a generally useful partitioning method, we propose DEEPLY. This new algorithm extends the CO-GCN deep learning partition generator with (a) a novel loss function and (b) some hyper-parameter optimization. As shown by our experiments, DEEPLY generally outperforms prior work (including CO-GCN, and others) across multiple datasets and goals. To the best of our knowledge, this is the first report in SE of such stable hyper-parameter optimization. To aid reuse of this work, DEEPLY is available on-line at https://bit.ly/2WhfFlB.
- 22 October 2019
- Published by Springer Nature
- p. 64-68
Towards Automated Planning for Enterprise Services: Opportunities and Challenges
- 22 October 2019
- Published by Springer Nature
- p. 64-68
Towards Automated Planning for Enterprise Services: Opportunities and Challenges
- Open Access
Technical Health Check For Cloud Service Providers
Understanding the overall health of an IT Infrastructure is a key part of IT Service Management. Traditional approach to perform technical health check is by visiting customer's physical site and rigorously examining the IT infrastructure with Subject Matter Experts. Alternatively, periodic surveys are sent to Technical Architects who are responsible for the managed IT infrastructure. In essence, both site visits and surveys suffer from reactive nature, and subjective assessment. In this paper, we present technical health check for cloud providers, that monitors, assesses operational data and depicts the current health of an IT infrastructure in real time. We also discuss challenges and opportunities of technical health check in Hybrid Cloud Environment.
Open AccessTechnical Health Check For Cloud Service Providers
Understanding the overall health of an IT Infrastructure is a key part of IT Service Management. Traditional approach to perform technical health check is by visiting customer's physical site and rigorously examining the IT infrastructure with Subject Matter Experts. Alternatively, periodic surveys are sent to Technical Architects who are responsible for the managed IT infrastructure. In essence, both site visits and surveys suffer from reactive nature, and subjective assessment. In this paper, we present technical health check for cloud providers, that monitors, assesses operational data and depicts the current health of an IT infrastructure in real time. We also discuss challenges and opportunities of technical health check in Hybrid Cloud Environment.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 22 (6) , 54-59
A Conceptual Framework for Engineering Chatbots
The increasing popularity of chatbots as virtual assistants has lead to many organizations releasing If-This-Then-That frameworks to engineer such chatbots. However, these frameworks often result in inflexible and difficult-to-maintain chatbots. This paper outlines a high-level conceptual framework for realizing flexible chatbots founded upon agent-oriented abstractions: goals, plans, and commitments.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 22 (6) , 54-59
A Conceptual Framework for Engineering Chatbots
The increasing popularity of chatbots as virtual assistants has lead to many organizations releasing If-This-Then-That frameworks to engineer such chatbots. However, these frameworks often result in inflexible and difficult-to-maintain chatbots. This paper outlines a high-level conceptual framework for realizing flexible chatbots founded upon agent-oriented abstractions: goals, plans, and commitments.
- 1 January 2018
- Published by IBM in IBM Journal of Research and Development
- Vol. 62 (1) , 8:1-8:11
Building a cognitive platform for the managed IT services lifecycle
- 1 January 2018
- Published by IBM in IBM Journal of Research and Development
- Vol. 62 (1) , 8:1-8:11
Building a cognitive platform for the managed IT services lifecycle
- 1 November 2017
- Published by IBM in IBM Journal of Research and Development
- Vol. 61 (6) , 7:1-7:12
Real-time understanding of humanitarian crises via targeted information retrieval
- 1 November 2017
- Published by IBM in IBM Journal of Research and Development
- Vol. 61 (6) , 7:1-7:12
Real-time understanding of humanitarian crises via targeted information retrieval
- 1 March 2016
- Published by IBM in IBM Journal of Research and Development
- Vol. 60 (2-3) , 12:1-12:11
API Harmony: Graph-based search and selection of APIs in the cloud
- 1 March 2016
- Published by IBM in IBM Journal of Research and Development
- Vol. 60 (2-3) , 12:1-12:11
API Harmony: Graph-based search and selection of APIs in the cloud
- 2 September 2015
- Published by Springer Nature
- p. 225-235
Towards a Model for Resource Allocation in API Value Networks
- 2 September 2015
- Published by Springer Nature
- p. 225-235
Towards a Model for Resource Allocation in API Value Networks