Portfolio

Projects & Research

Flagship case studies translating research into production systems that enterprises trust.

Applied MLRAG Security & AI SafetyIn Deployment

RAGWall: Prompt Injection Detection for Retrieval-Augmented Generation (RAG) Systems

~90% detection on public prompt-injection with transformer, ~70% regex-only (<1ms). ~48% HRCR reduction on healthcare corpus. Zero observed false positives on tested benign sets.

~90% PromptInject with transformer

View case study

Additional projects in healthcare AI, decentralized systems, and education innovation are moving through the Haske Labs pipeline.