Last date to apply:

Thesis work within Embedded Software and AI

Agent-Based Generation of Release Documentation

We are looking for bachelor or master’s students in software engineering, computer science, artificial intelligence, or a related field who are interested in completing their thesis project within our embedded systems organization.

Background:

Release documentation is traditionally produced by engineers who review changes since the previous software release, identify what matters to users, and translate technical implementation details into clear descriptions of changed behavior, configuration, and limitations. This requires substantial contextual understanding and is difficult to automate with conventional rule-based methods.

This thesis explores whether an AI-based agent can generate reliable release documentation by combining evidence from a software repository with a document template and project-specific instructions for terminology, style, tone, and exclusions. The solution will be evaluated as part of an existing release process, with particular attention to documentation quality, traceability, robustness, and computational cost.

The objective

• Design, implement, integrate, and evaluate an AI-based agent that automatically generates human-readable release documentation for a software product.
• Investigate how much repository context is required to produce reliable documentation without excessive token consumption or loss of relevant information.
• Enable documentation for earlier releases to be reconstructed from repository history, including patches and re-releases.
• Evaluate whether the generated documentation is comparable in practical usefulness to documentation written by an experienced engineer, while clearly exposing uncertainty instead of inventing unsupported product knowledge.

Your skills and background

• Bachelor or Master’s studies in Software Engineering, Computer Science, Artificial Intelligence, Embedded Systems, Data Science, or a related program.

• Interest in software repositories, release processes, generative AI, large language models, agent workflows, and prompt or context engineering.

• Experience with software development, version control, and structured testing. Familiarity with CI/CD, technical writing, or evaluation of AI systems is beneficial.

• An analytical mindset and the ability to distinguish externally observable product changes from internal implementation details.

The thesis will include work such as

• Analyze the existing release process, documentation expectations, repository structure, metadata, and representative historical releases.
• Establish a baseline solution and develop methods for extracting and selecting relevant commits, diffs, configuration changes, and other repository evidence.
• Design an agent workflow that identifies significant changes, reasons about external impact, verifies statements against repository evidence, and creates the final document using the required template and metadata.
• Integrate the agent into the release workflow with defined inputs, outputs, configuration, and failure handling.
• Create a repeatable evaluation framework and acceptance-test dataset covering bug fixes, configuration changes, larger features, internal refactoring, and poorly documented commits.
• Measure documentation quality, omissions, unsupported additions, traceability, token usage, computational cost, limitations, and engineering trade-offs.
• Document the architecture, implementation, experiments, results, assumptions, and known limitations, and present the completed thesis.

Scope and expected outcome

The work focuses on release documentation derived from repository and release process evidence. Sourcecode documentation, marketing material, requirements verification, general-purpose document generation, and release approval are outside the scope. A project-specific prototype is acceptable; the primary outcome is well-supported knowledge about feasibility, architecture, limitations, quality, and cost.

Expected deliverables include a working agent prototype, release-process integration, configurable project-specific style rules, template and metadata support, repository-change extraction, historical reconstruction, an acceptance-test dataset, an evaluation framework with results, technical documentation, and the thesis report.

How to apply

Please submit your application with CV and cover letter as soon as possible. Due to GDPR, applications are not accepted by email.

Start date: To be agreed, but spring 2027, Q1 or Q2, depending on the size of the work.

For questions regarding the thesis project, please contact: Peter Lindsäth - [email protected].

Read about Husqvarna Group here:

https://www.husqvarnagroup.com/

Husqvarna Group is a world-leading producer of outdoor power products for garden, park and forest care. Products include chainsaws, trimmers, robotic lawn mowers and ride-on lawn mowers. The Group is also the European leader in garden watering products and a world leader in cutting equipment and diamond tools for the construction and stone industries.