Back to Context Engineering
Library
Structured output
JSON, schemas, function calling.
Prompting
Overview
Structured output forces an LLM to return machine-parseable data (JSON, schema-constrained) instead of prose. It's what makes model responses safe to feed into downstream code without brittle parsing.
How it works
PromptingClientServiceEdgeData
Step by step, with examples
- 1
Define
- Declare a JSON/enum schema.
- 2
Instruct
- Ask for schema-valid output.
- 3
Parse+retry
- Reject and repair invalid output.
- 4
Typed data
- Use it safely downstream.
- Example: function calling
Overview
Constrain outputs to a schema (JSON mode / function calling) so downstream code can parse reliably.
Common pitfalls
- No validation/retry on malformed output
- Over-nesting schemas
- Free text mixed with JSON
Where this content comes from
For full transparency, this content is curated and verified from these sources:
Frontier-lab prompting & agent guidesRetrieval-augmented generation literatureOppZen-authored context-engineering playbooks