# Private AI: running language models inside your boundary — Genyra > What private AI means, when a self-hosted LLM is required, what runs inside the boundary, how to size hardware honestly, and how it is operated. Canonical page: https://genyra.com/notes/private-ai-inside-the-boundary Private AI means the model, the documents it reads, the index it searches and the log of what it said all run inside an environment you control. It is the only arrangement some organisations can lawfully use, and it is a different engineering job from calling an API. ## What private AI means. Four components make up a working document-and-question system: the model runtime, the retrieval index, the document store and the audit log. Private AI is the arrangement where all four live inside one boundary the organisation controls, on its own premises or in a dedicated environment built for it, and nothing leaves that boundary to be processed elsewhere. The word "private" is doing real work. It is not a model hosted by a vendor with a privacy policy. It is infrastructure the organisation can inspect, with a list of permitted crossings written down before the first document is indexed. ## When it is required rather than preferred. Residency rules that forbid processing outside a jurisdiction. Confidentiality obligations to clients or patients that a third-party terms page cannot discharge. Regulators who will ask to see the log. Material that must never be used to train anyone else's model. In each case the question is not whether the vendor is trustworthy but whether the organisation can demonstrate control. A private deployment lets it. ## What runs inside the boundary. The runtime serves the model. The index turns documents into something the model can search. The store holds the documents and their versions. The log records every question, the sources retrieved, the answer, the model version and who approved it. Around them sit the identity service users sign in with, the audited path administrators use, and the monitoring that says whether the system is healthy. Residency is a design decision: where documents may be stored, where processing may happen and which jurisdictions are excluded are recorded as requirements and then met by placement and routing. Changing that list goes through the same change process as changing the model. - Model runtime, retrieval index, document store and audit log inside one boundary - Users through the organisation's identity service; administrators through an audited path - Residency and permitted outside services written down and enforced by design - Client documents, questions and answers never used to train a model unless asked for in writing ## Hardware and models, honestly. The hardware depends on the models and the workload: how many people ask questions, how long the documents are, how fast an answer must come back. Memory on the accelerator is usually the constraint that decides which models are practical. We state the sizing for a particular environment after seeing the workload, not from a table, and we would be suspicious of anyone who does otherwise. Open-weight models run entirely inside the boundary and are the natural fit for private deployment. Where a controlled commercial model is justified, it is named in the design together with its version and the data that may reach it, and that is a different arrangement with its own contract. ## Deployed is not finished. A private system has an operator, monitoring, a version history for models and prompts, an evaluation set that is run again when anything changes, a change process, and a plan for incidents and cost. Answers cite their sources and a named reviewer approves or sends back, so the record shows what the system said and what a person decided. The organisation can operate it, be trained to, or hand it over with the records. ## Who does this work. Custom AI work described on this site is contracted with Genyra L.L.C-FZ in Dubai, a separate company that operates genyra.ai. The design, the infrastructure and the operating duties are discussed in an enquiry; available hardware and hosting are confirmed for the particular environment. ## Related work - [Private AI deployment](https://genyra.com/ai/private-deployment): Private AI deployment: self-hosted LLMs, retrieval and audit logs on-premise or in a dedicated environment. Residency by design, no training on your data. - [Custom AI solutions](https://genyra.com/ai): Custom AI development for organisations: built around a real workflow, run inside your boundary, reviewed by people and recorded. Genyra L.L.C-FZ, Dubai. - [Managed AI operation](https://genyra.com/ai/managed-operation): Managed AI services for deployed systems: an operator, monitoring, version history for models and prompts, evaluation, change control and incident planning. Contact: contact@genyra.com Genyra LLC and the Dubai business Genyra L.L.C-FZ / Genyra.ai are distinct entities. Project scope and the contracting entity are agreed explicitly.