yigityildiz0 Data Context
Make data meaning discoverable before analysis or automation.
- Inventory datasets/tables, owners, grain, keys, update cadence, and access constraints.
- Define metrics with numerator, denominator, filters, time window, source, owner, and known caveats.
- Document relationships and transformations without pretending unverified lineage is factual.
- Keep an index concise and link deep detail by subject area.
- Review stale definitions, duplicates, and conflicting names before creating a new metric.
Do not scan unauthorized systems or preserve secrets. A data context is documentation, not a guarantee that the underlying data is correct.