Home › Key concepts › Structured output
Key concept · Crawl (beginner) · the same on every platform
Structured output
Ask the model for JSON in a fixed shape, then check it in code.
What it is
Instead of free text, you give the model a schema (fields and types) and ask it to answer in that shape. Your code validates the result and retries or fails clearly if it does not fit.
Why it matters
Free text is hard to use safely. A checked structure can go straight into code and databases.
An example
From an email, the model returns {"claim_date": "2026-10-12", "vehicle": "KA01AB1234"} and code checks the date is not in the future.
The common mistake
Parsing the model's prose with regular expressions and hoping.
Where you meet it on each platform
The idea stays the same; only the product name changes.
| Job | AWS | Azure | Google Cloud | Databricks | Open source |
|---|---|---|---|---|---|
| Prompts and structured outputask clearly and get JSON back you can check | Bedrock Converse API | Foundry structured outputs | Gemini controlled generation | ai_query + structured output | Pydantic + JSON mode |
Related ideas
Where it shows up
Part of the Crawl level on these paths: AI Engineering (working with models).