Three ways I help teams ship AI that holds up.
Agentic systems & RAG
Research agents, multi-agent orchestration and retrieval pipelines, designed to run securely on AWS Bedrock/SageMaker or on-prem.
- LangGraph
- MCP
- Bedrock
- Knowledge graphs
AI for investigations & intelligence
AI-assisted fraud investigation, integrity and senior-management due diligence, and market intelligence. Findings come out structured, sourced and defensible.
- IDD / SMDD
- Fraud & AML
- Market research
AI audit, safety & evaluation
Audits of enterprise AI deployments, model-behaviour evaluation, prompt-injection testing and governance aligned to GDPR/CCPA, plus custom benchmarks.
- Evals
- Interpretability
- Governance