Glossary
Search Azure terms
Open a clear definition, then continue into exam context, architecture, commands, operational examples, common mistakes, and related concepts.
Search all
Commands
Learning guides
Concept graph
Compare
Search-first Azure knowledge base
Term results
Search for a term or click a category. Results render only after you ask for them, so the glossary does not dump every available term on first load. Each result includes Quick peek and Open full term page actions.
Start with a search or a category.
Try managed identity , resource group , az group , private endpoint , or click Databases to load all database-related terms.
AI and Machine Learning
verified
Online deployment
An online deployment is the Azure Machine Learning serving configuration behind an online endpoint. It defines the model, scoring code, environment, instance type, instance count, and request settings used for real-time inference, while the endpoint controls authentication, scoring URI, traffic routing, and invocation.
Azure Machine Learning
intermediate
6 commands
Aliases: Azure ML online deployment, managed online deployment, blue deployment, green deployment, online deployment, model-serving deployment
Quick peek
Open full term page
AI and Machine Learning
verified
Online endpoint
An online endpoint in Azure Machine Learning is an HTTPS endpoint for real-time inference. It exposes deployed models to synchronous clients, defines endpoint name, region, authentication mode, scoring URI, and traffic allocation, and can host one or more online deployments.
Azure Machine Learning
fundamentals
6 commands
Aliases: Azure ML online endpoint, managed online endpoint, real-time inference endpoint, scoring URI, online endpoint
Quick peek
Open full term page
AI and Machine Learning
verified
OpenAI deployment name
An OpenAI deployment name is the customer-chosen name assigned to an Azure OpenAI or Foundry model deployment. Applications use that name, not necessarily the base model name, to route inference requests to the deployed model, quota, version, and deployment type.
Azure OpenAI
intermediate
6 commands
Aliases: Azure OpenAI deployment name, model deployment name, deployment_name, Azure OpenAI model parameter, OpenAI deployment name, deploymentName, deployments route
Quick peek
Open full term page
AI and Machine Learning
verified
Read model
In Azure AI Document Intelligence, the Read model is the prebuilt OCR model that extracts printed and handwritten text, words, lines, bounding locations, and languages from documents and images. It is also the text foundation used by layout, prebuilt, and custom document models.
Document Intelligence
fundamentals
5 commands
Aliases: Document Intelligence Read model, prebuilt-read, Read OCR, OCR read model, Azure AI Read model
Quick peek
Open full term page
AI and Machine Learning
template-specs-upgraded
Run
Microsoft Learn describes an Azure ML job as an execution of a task against a compute target, including command, sweep, and pipeline job types. In day-to-day usage, a run is the tracked execution record with status, logs, inputs, outputs, metrics, and artifacts.
Azure Machine Learning
intermediate
6 commands
Aliases: Azure ML run, machine learning run, training run, job run, ML experiment run
Quick peek
Open full term page
AI and Machine Learning
template-specs-upgraded
Safety system message
Microsoft Learn explains that safety system messages guide Azure OpenAI model behavior, improve response quality, and reduce the likelihood of harmful outputs. They are one layer in a broader safety strategy and are also described as system prompts or metaprompts.
Microsoft Foundry
intermediate
5 commands
Aliases: Azure OpenAI safety system message, safety metaprompt, system prompt safety guidance, Foundry safety message, AI safety instructions
Quick peek
Open full term page
No glossary terms matched that search.
Try a service name, acronym, command group, or category such as RBAC , az group , App Service , Application Insights , Databases , or Azure AI Search .
Clear filters and show matches
Reset search
