Security & Permissions

AI agents run inside the same security boundaries as any other Simplio3D API client. Connecting an assistant does not create a new privilege path into your data.

Writes are controlled by construction

Every tool is registered as read-only or as a fully-declared write tool — the registry refuses anything in between. Write tools never mutate directly: they build a plan, and high-risk changes (pricing, SKUs, deletions, bulk edits, shared materials) only execute after the workspace user confirms the plan in the app. Every applied change is snapshotted (undoable), re-validated, audited and rate-limited. Publishing, integrations, customer communication and asset uploads remain out of reach entirely.

What every call passes through

  1. Authentication and billing. The same gates as the rest of the API: a verified account with an active plan or trial.
  2. Workspace scoping. Requests act on one workspace. Data is addressed by the authenticated account’s own keyspace, so an id belonging to another tenant simply resolves to “not found” — it can never cross the boundary.
  3. Per-tool permissions. Each tool declares the permission it requires — read tools a read permission, write tools a write permission — and is refused for workspace roles that lack it. A Viewer seat can never invoke or confirm a write.
  4. Schema validation. Arguments are validated before a tool runs; unknown fields are rejected rather than ignored.
  5. Result sanitization. Results are filtered before they reach the model: credential-shaped fields are redacted, oversized payloads are capped, and any truncation is marked so a model cannot mistake a partial answer for a complete one.
  6. Audit logging. Every execution is recorded with the tool name, account, workspace, duration, and outcome. Argument values and results are never logged.

Never exposed to a model

Database or direct storage access
Service credentials and platform keys
SMTP passwords and webhook signing secrets
WooCommerce and Shopify store credentials
Share-view passwords
Raw scene data and inline image blobs

Project settings are additionally filtered through the same credential denylist used for public share links, and the tool reports which fields it withheld.

Operational advice

  • Give agents a token from an account whose access matches the job — use a Viewer seat for read-only analysis rather than an owner token.
  • Rotate the token if it may have been exposed; revoking the seat immediately stops all tool access.
  • Remember that anything an agent reads may be sent to your AI provider. Treat customer quote requests accordingly.

Continue reading