<!-- https://staircase.co/agents/roster/dataset-fulfilment -->
# Dataset fulfilment

# Dataset fulfilment

Data

<!--source:agent-kits-->
Turns an approved data request into a scoped extract — resolving which organisation it belongs to, mapping the requested field names onto the canonical model, and returning either the result directly or a time-limited download link.
<!--/source-->

- **Used when**
<!--source:agent-kits-->
— When someone with authority to ask needs data out of the graph store and the request arrives as a sentence rather than as a query.
<!--/source-->

- **Loads first**
<!--source:agent-kits-->
- The persistence product's own access patterns, before any read.
<!--/source-->
<!--source:agent-kits-->
- Its access bootstrap, which establishes the environment and the verified credential source.
<!--/source-->

- **Returns**
<!--source:agent-kits-->
- How it was invoked, how it read the request, and the organisation scope it resolved.
<!--/source-->
<!--source:agent-kits-->
- The environment, verified credential source and discovered configuration, with no secret values.
<!--/source-->
<!--source:agent-kits-->
- What validation found — a missing scope, an unverified requester, an unmapped field.
<!--/source-->
<!--source:agent-kits-->
- The extraction plan: requested field names, the canonical fields they map to, and anything unmapped.
<!--/source-->
<!--source:agent-kits-->
- The action taken, the workflow status, and the artifact metadata the workflow returned.
<!--/source-->
<!--source:agent-kits-->
- The exact missing input, when it is blocked.
<!--/source-->

## Others in Data

- Counterparty document expectations
- Data-lake assistant
- Knowledge search
- Metric reconciliation
- Model curator
- Pipeline control panel
- Property data exploration
- Public record ingestion
- Question answering
- Report catalog
- Search to production
