Capabilities Querying

Ask in plain words, or write SQL. Both are governed.

A quick query takes a question in plain words, resolves the names to golden records through the cross-reference, applies your policy and generates SQL against the bed; the answer cites the rows it used and the query is yours to edit and save.

“Open orders for Acme in Q3, by plant”typed or spokenWHAT HAPPENS1 · resolve Acme → golden L-00731 (4 keys)2 · pick the saved measure open_order_qty3 · apply the reader's row and column policy4 · generate SQL against the bed5 · run, cite, keep the querySELECT plant, sum(open_qty)FROM bed.sales_order_line lJOIN golden.customer_xref x ON l.kunnr = x.source_keyWHERE x.golden_id = 'L-00731' AND l.period BETWEEN ... GROUP BY 1editable · saveable · shareablethe same box accepts SQL directly for people who prefer to write it
A question becomes governed SQL with the cross-reference applied; the same box accepts SQL directly.
2
ways in: plain words or SQL
product
100%
of answers with the rows they used
product
1
policy for the quick query, the SQL box and BI through JDBC
product
0.9 s
for the four-key resolution and the plant roll-up on the showcase estate
showcase
What you see

The quick query, and the SQL it wrote

askOpen orders for Acme in Q3, by plant, in euros
-- generated, governed, editable
SELECT s.name AS plant, SUM(l.open_qty) AS open_qty, SUM(l.open_value_eur) AS open_value_eur
FROM bed.sales_order_line l
JOIN golden.customer_xref x ON l.customer_source_key = x.source_key
JOIN golden.site s ON l.plant = s.sap_plant
WHERE x.golden_id = 'L-00731' AND l.period BETWEEN '2026-Q3' AND '2026-Q3'
GROUP BY 1 ORDER BY 3 DESC;
-- resolved: Acme → L-00731 (4 source keys) · policy: row filter company code 1200 · 184 rows · 0.9 s

The generated SQL is shown, editable and saveable; a click on the resolution line shows the four source keys behind Acme; a click on the policy line shows the row filter that applied. The answer opens as a grid and can become a pivot or a chart with one click.

Step by step

How a question becomes an answer

Resolve the names'Acme' resolves to golden supplier L-00731 through the same lookup the API uses; an ambiguous name asks which one.
SQL for analysts

The bed as a database

Through JDBC and ODBC the bed is a database: golden views per domain (golden.customer, golden.supplier, golden.material), the cross-reference tables, the hierarchies with their versions, the calendars, and the transactions read in place or from the governed replica. AS OF works on every table. The security engine rewrites the query with your policy before it runs.

Saved queries are objects: versioned, shareable, callable from the API as rows, usable as the source of a pivot, a chart or a rule.

Golden viewsgolden.customer · golden.supplier · golden.material · …
Cross-referencegolden.customer_xref (golden_id, system, source_key)
Hierarchieshier.product (version, node, parent, level, valid_from, valid_to)
Calendarscal.fiscal · cal.planning
AS OFon every table
Policyapplied by rewriting the query
Terms on this page

Quick queryA question in plain words that becomes governed SQL with the cross-reference applied.
CitationThe rows an answer used, one click away.
Saved queryA versioned, shareable query usable by pivots, charts, APIs and rules.
Questions

Which model answers the quick query?

A language model reads the question and the model of the bed (names, measures, dimensions); it sees no row data. The SQL it writes runs under your policy. See AI-assisted.

What if the generated SQL is wrong?

It is shown, so a reader can check and edit it; every answer cites its rows; a saved query is reviewed before it is shared.

Can ChatLima use this?

ChatLima is the same quick query inside the conversational interface, with the same policy and citations.

See your first domain built on your data

Bring two systems that hold the same customers, suppliers or materials. In one working day we connect them, run the match on live rows, review the queue with your steward and publish the first golden view with its API.