The AI glossary for regulated teams
Short, checkable definitions of the terms that decide whether an enterprise AI project is trustworthy: sovereignty, residency, retrieval, grounding and governance. Written for people who have to defend the answer, not just demo it.
Last updated 2026-09-18 · plain-text version for AI tools
Sovereign AI
Sovereign AI is artificial intelligence that runs entirely under one organisation's or country's legal and physical control: the models, the data, the logs and the infrastructure all stay inside a chosen jurisdiction, and no third party can access or retain the content.
Uthereal Cortex runs on Swiss infrastructure or inside your own data centre, with an egress record that shows every outbound call - or the absence of one.
Read the full definitionData residency
Data residency is the guarantee that a defined set of data is stored and processed in a named country or region. For AI systems it must cover four things: the source documents, the vector index, the prompt and answer logs, and the model inference itself.
With Uthereal, storage, index, logs and inference all sit in the same chosen region - Switzerland by default, or your own infrastructure.
Read the full definitionPrivate AI
Private AI is an AI deployment in which your content is never sent to a shared public model service and is never used for training. It runs in a single-tenant environment - your cloud account, your data centre, or a dedicated sovereign region - with isolated storage and isolated inference.
Uthereal ships the same product in three shapes: Swiss-hosted, your cloud tenant, or fully on-premise with no outbound network path.
Read the full definitionRAG (retrieval-augmented generation)
RAG, or retrieval-augmented generation, is a pattern where a system first retrieves relevant passages from your own content and then asks a language model to answer using only those passages. The model supplies the language; your documents supply the facts.
Cortex is a managed RAG stack: ingestion, chunking, hybrid retrieval, reranking and cited generation, available through an API and the Uthereal SDK.
Read the full definitionGrounding
Grounding means constraining an AI answer to specific retrieved evidence, so that every statement can be traced to a passage in a known source. An ungrounded answer is generated from model memory alone and cannot be verified.
Cortex answers carry passage-level citations with document, page and section, and return an explicit no-answer when the evidence is missing.
Read the full definitionHallucination
A hallucination is a confident AI statement that is not supported by any source. It happens because language models predict plausible text rather than look facts up, so gaps in retrieval get filled with fluent invention.
Cortex reports the evidence behind each answer, so an unsupported claim is visible rather than hidden in fluent prose.
Read the full definitionChunking
Chunking is the process of splitting documents into passages small enough to retrieve precisely and large enough to stay meaningful. Chunk boundaries decide what an AI system can find, so poor chunking silently caps answer quality.
Uthereal chunks by document structure and keeps page and section metadata, which is what makes page-accurate citations possible.
Read the full definitionEmbedding
An embedding is a numeric vector that represents the meaning of a piece of text, so passages with similar meaning sit close together in vector space. Embeddings let a system retrieve by meaning rather than by exact keyword match.
Cortex runs hybrid retrieval with reranking, and can run embedding inside your own environment when sovereignty is required.
Read the full definitionVector database
A vector database stores embeddings and returns the nearest matches for a query vector. It is one component of a retrieval system, not a complete one: it does not parse documents, enforce permissions, rerank results or produce citations.
Uthereal replaces the assembly job: retrieval, permissions and citations arrive as one API instead of six components to integrate.
Read the full definitionKnowledge Object
A Knowledge Object is a self-contained unit of expertise - the content, its structure, its provenance, its permissions and its validity period held together - so an AI system can use it, cite it and enforce rules about it. It is Uthereal's alternative to loose files and raw text chunks.
Knowledge Objects are the unit Cortex ingests, governs, retrieves and licenses.
Read the full definitionKnowledge Agent
A Knowledge Agent answers questions from a governed body of source material and cites the passages it used. Its job is to know: it retrieves, reasons over evidence and refuses when the evidence is missing, rather than taking actions in other systems.
Cortex ships both agent types on the same governed knowledge layer, so a workflow agent inherits the same permissions and citations.
Read the full definitionContext engineering
Context engineering is the discipline of deciding what an AI model sees at the moment it answers: which passages, in what order, with which metadata and instructions. It has replaced prompt wording as the main lever on answer quality.
Uthereal treats context assembly as a product surface: retrieval, reranking, deduplication and budget control are configurable rather than hidden.
Read the full definitionWhite-label AI chatbot
A white-label AI chatbot is an assistant you deploy under your own brand, domain and design, with no vendor badge and no vendor branding in the interface. The vendor supplies the engine; the customer owns the experience and the data.
Uthereal ships white-label assistants on your domain, Swiss-hosted, with no 'powered by' badge and typical launch in two to four weeks.
Read the full definitionPermission-aware retrieval
Permission-aware retrieval applies each user's access rights at query time, so the system can only retrieve passages that user is already allowed to read. Filtering after generation is too late: the content has already entered the answer.
Cortex carries source permissions into the index and enforces them per request, with an audit trail of what was retrieved for whom.
Read the full definitionEU AI Act
The EU AI Act is the European Union's risk-based regulation of artificial intelligence. It classifies systems by risk level and imposes duties on providers and deployers, including transparency, human oversight, data governance and technical documentation for higher-risk uses.
Cortex produces the artefacts compliance teams ask for: source citations, retrieval logs, access records and an egress record.
Read the full definitionEgress record
An egress record is a log of every outbound network call an AI deployment makes, including the destination, the payload class and the time - or a signed statement that no outbound call occurred. It turns 'your data stays here' from a promise into evidence.
Uthereal on-premise deployments ship an egress record by default, showing the absence of outbound traffic rather than asserting it.
Read the full definition