Featured AI Navigator

Safety Navigator

Helping society adopt new technologies safely

Modern technology systems, from climate adaptation to infrastructure protection and more, are evolving faster than traditional assurance methods can handle. This makes it hard to deploy at scale and pace while ensuring that systems remain safe and are used safely. With increasing pressure to adopt new technologies rapidly, the risk grows that functionality may be deployed without robust safety assurance, exposing individuals and wider society to hazards of unknown magnitude.

Hence, we received government funding to develop, in partnership with the Centre for Assuring Autonomy at the University of York, an AI assistant that supports safety engineers in maintaining credible safety cases and managing associated risks amidst rapid change. The resulting product, Safety Navigator, enables deep analysis of system dependencies, assumptions, evidence, risks, mitigations, and regulatory compliance. The architecture allows it to adapt across domains while maintaining alignment with safety assurance best practices, making it ideally suited for multipurpose systems under continual change.

The University of York verified that Safety Navigator’s outputs meet all UK government Data Quality dimensions – all information provided is correct, complete, consistent, current, concise, and checkable. This is possible due to Dedoctive’s unique architecture.

Safety Navigator does not replace safety and risk professionals . Rather, it augments their efforts, by parsing technical documentation rapidly to provide engineering-grade graphical outputs that help human experts focus their attention on high priority issues. This is particularly valuable when change requests cut across multiple functional areas or introduce new system dependencies.

By highlighting deltas in safety cases and guiding mitigation efforts, the tool helps ensure that risks remain As Low As Reasonably Practicable and tolerable without slowing innovation. This reduces the time and cost required to deploy new technologies, enhancing an organisational user’s ability to field cutting-edge capabilities while maintaining rigorous safety standards.

Features

The version of Safety Navigator developed with government funding automatically transforms safety documentation into Goal Structuring Notation (GSN, a visual format that clarifies the logic and evidence of safety cases), while analysing the argument to identify potential weaknesses, inconsistencies, or evidence gaps that require further attention.

We have since extended Safety Navigator to support risk management and compliance assessment.

Risk management. Bowtie diagrams are essential tools for mapping complex risk scenarios and ensuring robust safety controls, but creating them has always been a slow, manual process. With Safety Navigator, the user can select a GSN node (e.g., representing operating context, a claim, an assumption, or a piece of evidence) to see a bowtie diagram showing the threats and consequences associated with the node being invalid.

Compliance assessment. Safety Navigator automatically creates from engineering documents and data an overview document (e.g., a Production Readiness Review or Safety Case Report), then lets the user customise the document with agentic automation. It then evaluates the system against applicable policies, regulations, and standards, updating the document to recommend approval / rejection and mandate appropriate conditions / amendments.

As with all Dedoctive products, all Safety Navigator outputs are fully trustworthy and verifiable. Being drawn only from a “knowledge model”, outputs are guaranteed to be correct, complete, consistent, current, concise, and checkable. Each statement is accompanied by hyperlinks to the original sources, and these hyperlinks are also presented in a visual mind-map. Workflows use the open BPMN standard, and can be customised using a simple visual tool.