Glossary · Agentic AI
What is Structured outputs? Definition and meaning
Constrains generation to a JSON schema or type so that results are always parseable.
Definition
Structured outputs: Constrains generation to a JSON schema or type so that results are always parseable.
In short: Forcing model output into a schema.
When it is used
Reliable extraction and integration with downstream code.
Where it fits
Structured outputs belongs to Protocols in the Agentic AI topic. These are the other terms in the same group:
- MCP: An open protocol, created by Anthropic, that lets a model use tools, data sources and prompts exposed by servers.
- A2A: An open protocol, now under the Linux Foundation, with which agents discover each other and delegate tasks.
- Function calling: A model returns a structured call to a named function with arguments, and the application runs it and returns the result.
- OAuth for tool access: Uses OAuth flows so an agent acts on a user's behalf with scoped, revocable permissions.
Learn more
The full guide to Structured outputs explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Statistics · Next term: StyleGAN