Schema Features Reference
Every field in a template supports advanced features beyond the basic name and type. These features control how values are extracted, validated, transformed, and delivered.
Field features
| Parameter | Type | Description |
|---|---|---|
| Format constraint | regex | Validates extracted values against a regex pattern. Failing values can be emptied, flagged, or replaced with a constant. |
| Modifiers | pipeline | Post-processing transforms applied in order: format (date/number), alias (value mapping), max_length (truncation). |
| Constraints | validation | Rules evaluated after modifiers: required, enum, date-format, length, cross-field expressions. |
| Bypass strategy | skip LLM | Fields that don't need extraction: constant (fixed value), generator (auto-ID), reference (lookup from reference table). |
| Reference table | key-value | Inline lookup table for code mapping (e.g., country name → ISO code). Also supports multi-hop resolution chains. |
| Manual instruction | text | User-written extraction directive. Overrides the AI-synthesized master instruction from the field registry. |
| Capture submoves | array | Ordered execution: match (field matching), compute (calculation), reason (LLM inference). |
| Output name | string | Renamed field in export output. The internal name stays the same. |
For the complete JSON Schema specification with all features, see the Full Schema Reference in the Platform Guide.