Security
Controls you can verify. Limits we state plainly.
Synthetic data is a confidential asset. Automated checks reduce risk; they cannot prove that nothing about the original can be learned, and a downloaded file cannot be recalled.
What this build does
| Capability | Status | Notes |
|---|---|---|
| Assistant (built-in, rules-based) | live | Runs inside the deployment; no data leaves. |
| Assistant (Claude via Anthropic API) | available | Optional. Sees descriptions and synthetic aggregates only; never records. Enabled per organisation by an administrator. |
| File upload and schema-only definitions | live | Uploads are encrypted on receipt; the web and assistant processes cannot read them back. |
| Database, storage and warehouse connectors | not available | Contract defined; not live in this build. |
| Synthetic generation with quality, privacy and usefulness checks | live | Statistical generator; not differentially private. Checks are empirical indicators, not guarantees. |
| Partner workspaces with approved analyses | live | Restricted worker on synthetic data only; budgets and output limits. |
| Partner code execution | disabled | No isolated runtime is configured. Vendor code execution is disabled (fails closed). |
| Real-data model testing | live | Separate service; partners see reviewed, rounded results only. |
| Customer-controlled or regional deployment, single sign-on, managed keys | not available | Planned; this build is a single-host deployment. |