AI assistant — Map
A guided prompt that collects the source shape, the destination shape, and the rules between them — then generates the XSLT for an Art2link map.
Maps fail in a particular way: the XSLT compiles, the map runs, and a field comes out empty or wrong — because the assistant guessed at a field that wasn’t obvious from the schema names alone. The guided mode is built to prevent that class of failure by forcing the source shape, the destination shape, and the field-level intent to all be on the table before any XSLT is written.
What this mode builds
An Art2link map — the XSLT stylesheet, the source and destination shape references, and any custom-function calls via {{Function.fnX}} or art:invoke — ready to save in the mapping UI. The result is reviewed and saved by you; the assistant does not deploy it.
What the guided form collects
The form asks for the facts the assistant cannot infer:
- The source shape — sample, schema, or both.
- The destination shape — sample, schema, or both.
- Field-level mapping intent — which source field feeds which destination field, including any field whose mapping is not obvious from name similarity.
- Per-field transformations — format conversions, casing, defaulting, conditional logic.
- Lookups or enrichments — whether a destination field needs data from a custom function (database lookup, API call, computed value) and which function to use.
- Loop and grouping rules — how many destination records correspond to how many source records, and what the grouping key is.
- How missing or empty source data should be represented in the destination.
When to use it vs free-form
Use this guided mode whenever you have a source shape, a destination shape, and the rules between them. Use free-form when the request is closer to “explain why this existing map is producing an empty BuyerName” than to “generate the map.”
Limits
The generated map still needs review. The assistant works from the field-level intent you provide; it cannot verify that the resulting XSLT produces the values the downstream system actually wants. Run a representative source message through the map and check the output before saving the map into production traffic.