applied research

SafetyLM

the WHS assistant that shows its working.

SafetyLM began in the lab as one question: can AI answer WHS questions without inventing the law? it is now a commercial product for AU/NZ practitioners. it answers from a practitioner's knowledge base and public regulator guidance, checks every section it cites against those sources, and declines when it can't verify a figure.

passages indexed from 338 documents

30,000+

jurisdictions across AU and NZ

10

guided tasks, from SWMS review to board papers

14

the leading indicator project

finding the signals that move before harm does.

most safety dashboards report what already happened. this project catalogues the indicators organisations actually track, then tests which ones genuinely lead: which signals shift before incidents, and which are just noise with a good reputation.

the work-as-done field method

a field method for the work no procedure describes.

every organisation has a gap between work-as-imagined and work-as-done. this project turns the study of that gap into a repeatable field method: learning teams, friction mapping and procedure-vs-practice comparisons that produce findings you can compare across sites.

the pulse instrument

psychosocial risk, measured at the speed it moves.

long-form psychosocial surveys are rigorous but exhausting, so they run once a year and age immediately. we are exploring a short-form monthly check-in that line leaders can run themselves, designed to track against the long-form instruments rather than replace them.

the critical risk & control builder

bowties that do more than hang on the wall.

a visual bowtie builder that is easy to use and powered by AI. it understands the context and scope of your work and of your organisation, so the bowties it helps you build reflect how your sites really run. bowties you will use, rather than ones that live in a system by themselves.