Engineer working at a design workstation Team reviewing a drivetrain component Team reviewing a DSM interface Engineering team collaborating over technical drawings Engineer working at a design workstation Team reviewing a drivetrain component Team reviewing a DSM interface Engineering team collaborating over technical drawings

Turn engineering documents into a usable first-draft DSM.

AutoDSM uses large language models and retrieval-augmented generation to identify system components and dependencies from documents, helping teams draft Design Structure Matrices faster with less manual effort.

77.3%

Reproduced 357 of 462 DSM entries in the reported diesel engine validation study.

< 4 min

Prototype runtime achieved on a standard laptop-class machine.

No-code

Designed to support practical testing, validation, and future workflow development.

Built for faster DSM generation

DSM creation is often manual, interview-heavy, and slow. AutoDSM is positioned as a practical front-end workflow that helps you get to a draft matrix faster, using your document base as the starting point.

Reduce manual effort

Start from existing reports, manuals, and technical documents instead of building the matrix from scratch.

Use organisation-specific data

Ground outputs in proprietary data so results can reflect your own naming, scope, and system boundaries.

Draft components and dependencies faster

AutoDSM is designed to identify likely system elements and map likely relationships into a first-pass DSM.

Support human review, not blind automation

The output is most useful as a reviewable starting point that experts can validate, refine, and complete.

How it works

AutoDSM breaks source documents into searchable chunks, retrieves relevant passages, then uses an LLM to propose system elements and dependency entries for the matrix.

1

Load source documents

Technical documents are split and embedded so relevant passages can be retrieved later.

2

Identify elements and links

Structured prompts query the retrieved content to find major components and likely dependencies.

3

Generate a reviewable DSM

The outputs are assembled into a matrix that can be inspected, refined, and used as a practical starting point.

Supporting article

Download the published AutoDSM article for background, methodology, and validation details.

Contact us

Want to use AutoDSM or discuss your workflow? Reach out by email and we can continue from there.