Data Privacy
Private AI vs Public AI
The question is usually posed as a choice between two products. It is really a choice about which risks an organization would rather carry, and it does not have one answer that survives across every kind of content a bus...
RAG vs Fine-Tuning
Two ways to make a general model useful for your organization. Retrieval finds relevant material and supplies it with the question. Fine tuning continues training the model on examples so its behavior changes.
They are ...
Vector Databases and Enterprise AI
A vector database stores the numerical representations that make meaning based search possible, and answers the question of which stored items are nearest to a query. That is genuinely all it does. The engineering intere...
Protecting Sensitive Data When Using AI
An AI system is a new set of paths in and out of your information. Most of the work of protecting data around one is not novel: it is knowing which paths exist and putting a control on each. What is novel is that several...
AI Logging, Monitoring and Auditing
Every argument for logging an AI system is an argument for collecting the most sensitive material in the organization into one searchable place. Both halves of that sentence are true, and a design that takes only the fir...
AI Data Residency and Data Sovereignty
Data residency is a question about geography: where information is stored and processed. Data sovereignty is a question about jurisdiction: whose laws reach it, and who can compel its disclosure. They are related, they a...