Case Studies

Outcomes, not adjectives

A few engagements where the numbers did the talking - from knowledge-graph agents in production to fraud losses cut by three quarters.

Developer tooling / AI platform

A knowledge graph that made 7 AI agents cheaper and sharper

149 Entity types modeled 7 Specialist agents served 20+ Languages analyzed

As founding engineer at a US developer-tooling startup, I designed the knowledge-graph backbone for an automated software-analysis platform - turning raw context into structured graph slices that made a fleet of AI agents both cheaper to run and more accurate.

Read case study →
Legal / e-discovery

Reviewing 1M+ litigation documents at 99% accuracy

1M+ Documents processed 99% Classification accuracy -25% Retrieval time

As technical lead at a US litigation-data firm, I built the NLP/ML pipeline behind high-stakes litigation delivery - turning a manual review bottleneck into an accurate, auditable, automated process.

Read case study →
Fintech / banking

Cutting fraudulent transactions by 75% for a bank

-75% Fraudulent transactions +60% Lead engagement (chatbots) +40% Operational efficiency

Consulting independently across fintech and banking, I built a fraud-detection model that sharply cut losses - one of a series of predictive systems delivered for measurable business outcomes.

Read case study →