Thesis: Continuous application upgrade via Github agentic workflows

Keeping software secure and dependable involves frequent updates to dependencies, frameworks and APIs, often requiring substantial manual effort. This thesis explores whether risk-aware workflows involving multiple AI agents can automate this maintenance without compromising reliability or developer control. The aim is to build a proof of concept for continuous application upgrades.

The assignment

• Design and implement a maintenance workflow with GitHub Actions and AI agents that detects outdated dependencies, vulnerable libraries and deprecated API usage.
• Develop risk classification and task delegation so that low-risk changes can be implemented and tested autonomously, while higher-risk changes are submitted as pull requests for human approval.
• Explore coordination between specialized agents using tools such as GitHub Copilot agents, custom agents and GitHub Agentic Workflows.
• Evaluate the prototype’s maintenance capabilities, risk assessments, automated validation and potential to reduce manual work and maintenance time.
• Assess how execution logs and approval checkpoints support transparency and developer oversight.

Who we are looking for

• Studying towards a bachelor’s or master’s degree in computer science or an equivalent field.
• Expecting to graduate in June 2027.
• Fluent in both Swedish and English, in writing and speech.

What we offer

• Flexibility to adapt the project scope as implementation progresses, with priority given to core automation and risk-based decisions.
• A thesis environment at Knightec Group, which combines expertise in product and digital service development.

Practical details

Based at the Sundsvall office. Start in January or March 2027. Apply through the company’s careers page as soon as possible, no later than 30 November 2026. Questions can be sent to johanna.edstrom@knightec.se.