What the tool does
The user selects a general topic from a fixed list. When independently enabled, the server makes one provider call per API request. It supplies one to four scrubbed public units curated to the exact selected article range under request-local IDs u1 through u4; a whole page summary and sources outside that scope are not sent. The provider receives no user prose, source metadata, or server-owned display text. It returns only strict { "schemaVersion": 1, "orderedUnitIds": [...] } JSON containing an exact permutation. The server independently requires every ID exactly once and fails closed on any mismatch. It then renders immutable, prewritten review-stage bilingual unit text, each with one prebound official citation. The title, generic summary, caution, citations, and all citation metadata are server-owned. No model-authored legal prose is ever displayed.
Privacy by design
The request carries only the topic ID and locale. There is no field for a name, age, date, amount, document number, conversation text, or family narrative. The tool also keeps the selection and result out of the page URL, browser storage, and analytics.
Limits and availability
The tool explains a general topic and does not apply it to an individual family. It does not assess facts or evidence, compare the parties' positions, calculate an entitlement, choose a route, or predict an outcome. Its output is general legal information, not legal advice. This page remains in review, and the model connection stays disabled until the release, privacy, review, and evaluation gates are complete.