Structured outputs
Structured outputs are agent results returned as schema-validated, typed objects instead of free-form text. Downstream systems consume them directly — no prose parsing, no human re-interpretation — and a result that violates its schema is a hard failure rather than a confident-sounding guess.
In NeoXam Agents
Every task agent declares its input and output schemas in its descriptor, and outputs are validated against versioned schemas at run time. The reconciliation investigator, for example, returns a BreakAnalysis object: root cause class, confidence score, evidence links and a recommended action.
Related terms
See it at work
Business rule generation from plain language
Shipped (V0)Write 'flag NAV deviations above 2%' — the generator returns a syntactically valid business rule as a typed object DataHub consumes directly.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform