Glossary
Private LLM
A large language model deployed within a controlled, organisation-specific environment where data does not leave the organisation's infrastructure and is not used to train shared models.
A private LLM is a large language model deployed within a controlled environment — a specific cloud region, an organisation's own infrastructure, or a managed service with strict data isolation — where the organisation's data does not transit to shared model endpoints or contribute to model retraining.
In the context of Australian legal practice
LegalScout uses AWS Bedrock to provide private LLM inference within the AWS Sydney region. Your matter documents, client information, and firm knowledge are processed in-region — they do not reach OpenAI, Anthropic's public API, or any other overseas provider. This is the infrastructure pattern that satisfies the data sovereignty requirements of Australian legal practice.