Agents
Structured Output
Structured output constrains a model's response to a defined schema instead of free-form prose.
It lets the calling code parse the result reliably, without brittle regex or string matching.
It is foundational to tool calling and agent loops, where a wrongly-shaped response breaks the next step.
Enforcing and validating the schema is what makes it dependable, more than simply asking nicely for JSON.
← Back to the full glossaryRelated terms
More in Agents
Agent (Agentic AI) An agent is an LLM given a loop, memory, and tools it can call. Model Context Protocol (MCP) MCP is an open standard for connecting LLM applications to tools and data sources. Context Engineering Context engineering decides what occupies a model's context window at every step, and in what order. Idempotency An idempotent operation produces the same result no matter how many times it runs.