Look Up Data Product
Module · Stable
Look rows up in a data product by an exact filter (equals, not, contains, has, in, wildcard). Every row comes back with its row_id, trust level and owner.
The spreadsheet-world call on a data product. filter is an object of column key → value (equality) or → an operator object: {“not”: value}, {“contains”: text} (substring), {“has”: token} (one whole item of a comma-separated list, so C1 never matches C10), {“in”: [values]}, {“wildcard”: “BRK-*”}. Returns ROWS, never prose: each row carries row_id, trust (high / low / expired, computed from the product’s trust scheme), owner, confirmed_at / valid_until where the scheme has them, and its values. When no row matches, nothing_found is true — an explicit answer, not an empty guess. Each call is logged (row ids and trust, never values) as receipt.
When to use
Section titled “When to use”Use when you know which data product holds the answer (see List Data Products) and what to filter on — a country, a SKU, a part name. Cite the row_id of every row your reply relies on, and treat trust low or expired rows as unconfirmed.
When not to use
Section titled “When not to use”For an ordinary table that is not a data product, use List Records. When you do not yet know which product answers the question, call List Data Products first.
Inputs
Section titled “Inputs”Configured per use: dp, filter, columns, limit.
Outputs
Section titled “Outputs”Auto-generated from the skill registry (load_skills()). Do not edit by hand.