Thesis: Continuous application upgrade via Github agentic workflows

High Level Description Maintaining modern software applications requires continuous updates to dependencies, libraries, frameworks, and APIs to ensure security, reliability, and compatibility. These maintenance tasks are often repetitive and time-consuming, while some changes introduce risks that require careful review. Recent advances in AI agents and multi-agent systems create opportunities to automate application maintenance through GitHub Agentic Workflows. By combining autonomous agents with risk assessment, automated testing, and human oversight, routine maintenance tasks can potentially be handled with minimal manual intervention. This thesis investigates how risk-based multi-agent workflows can automate continuous application maintenance while maintaining appropriate levels of security, reliability, and human control. Project Description The student will design and implement an automated application maintenance workflow using GitHub Actions and AI agents. The workflow will continuously identify outdated dependencies, vulnerable libraries, and deprecated API usage, assess the risk associated with each issue, and delegate maintenance tasks to appropriate agents. The system will distinguish between low-risk and high-risk tasks: Low-risk tasks – Agents autonomously perform maintenance activities such as dependency upgrades, library updates, and API refactoring, followed by automated testing and validation. High-risk tasks – Agents analyze the issue, prepare proposed code changes, and create pull requests that require human review and approval before integration. The implementation will explore multi-agent orchestration, task delegation, risk classification, and automated validation using technologies such as GitHub Actions, GitHub Copilot agents, custom agents, and GitHub Agentic Workflows. The prototype will be evaluated based on its ability to automate maintenance tasks, correctly assess risks, validate changes, and reduce manual effort while maintaining transparency through execution logs and human approval checkpoints. The project scope can be adjusted depending on implementation progress, prioritizing core maintenance automation and risk-based decision-making. Who are we looking for? Bachelor or Master of Science in Computer Science or equivalent. Graduation in June 2027 Fluency in Swedish, both written and spoken Fluency in English, both written and spoken  Purpose The purpose of this thesis is to investigate how AI-driven, risk-based multi-agent workflows can improve the efficiency, security, and reliability of continuous software maintenance. The study will focus on the following areas: Automated application maintenance – Investigate how effectively AI agents can identify and resolve outdated dependencies, security vulnerabilities, and deprecated API usage. Risk-based autonomy – Evaluate how maintenance tasks can be classified by risk and how different levels of agent autonomy can be applied safely. Multi-agent orchestration – Investigate how specialized AI agents can collaborate and delegate tasks within GitHub Agentic Workflows. Quality assurance and validation – Evaluate how automated testing, validation checks, and human approval processes can ensure that AI-generated maintenance changes are reliable. Efficiency and human oversight – Investigate how much manual effort and maintenance time can be reduced while maintaining appropriate developer control, transparency, and accountability. The expected outcome is a proof-of-concept demonstrating how risk-based AI agent workflows can support continuous application upgrades and reduce the cost and complexity of software maintenance. An Exciting Journey with Knightec Group Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies – from idea to complete solution. Practical Information This is a thesis position, located at our office in Sundsvall . Start date January or March 2027. Please submit your application as soon as possible, but no later than 2026-11-30 . If you have any questions, you are welcome to contact johanna.edstrom@knightec.se . Note that due to GDPR, we only accept applications through our careers page.