Skip to content

Real engagements. Real outcomes.

Every case study is anonymised to protect our clients. The risks, methods, and results are real.

Financial ServicesLLM / GenAI Security

Red-Teaming a Customer-Facing GenAI Assistant

Adversarial testing of a retail bank's customer-facing GenAI assistant before a national rollout.

Critical prompt-injection paths closed pre-launch

Read case study
GovernmentAgentic AI Security

Securing an Autonomous Agent Pipeline in Government

Security review of a multi-agent automation pipeline handling citizen-service workflows.

Blast radius reduced through least-privilege agent design

Read case study
HealthcareWorkflow Automation Security

Mapping the Attack Surface of a Health Network's Automation Estate

First full attack-surface map of a health network's sprawling low-code automation estate.

Shadow automations and exposed webhooks brought under governance

Read case study
Critical InfrastructureEnterprise Consulting + Adversarial AI Testing

Securing AI on the Edge of an Energy Provider's OT Network

AI security uplift for an electricity provider adopting machine-learning analytics across IT and operational technology, under the SOCI Act.

AI analytics adopted without widening the OT attack surface

Read case study
RetailLLM / GenAI Security + DSPM

Safe GenAI Adoption for a National Retailer

Helping a national retailer roll out a GenAI shopping assistant while keeping customer data contained and classified.

GenAI assistant launched with customer data provably contained

Read case study
EducationEnterprise Consulting (AI Governance)

Standing Up AI Governance for a University

Building an ISO 42001-aligned AI governance framework so a university could adopt GenAI across teaching and research safely.

Campus-wide GenAI adoption under one governance framework

Read case study

Book a Free 60-Minute Briefing

A scoping discussion and threat-landscape overview with our ANZ specialists. No sales pressure.

Book a Briefing