TwinDocs
Connect your AI

Access and safety

Understand sign-in, channel boundaries, query modes, and the limits of a connection.

A Twin connection carries your identity to a bounded interface. Queries and discovery are read-only. A separately granted twin.write scope can publish an approved channel post, comment, reaction, native record, or version-checked saved-view update; it does not give an assistant general access to your workspace or server.

What sign-in decides

The service derives the following from the signed-in identity and administrator-managed mapping:

  • the active user;
  • the upstream and Twin organisations;
  • the permitted OAuth scopes;
  • the correct tenant control plane; and
  • the channels that user may access.

A query cannot supply or override those values. Missing, disabled, or mismatched mappings fail before execution begins.

What stays internal

Products, publications, relations, runtime capabilities, and model policy are internal governance and routing layers. They may determine how the Twin can answer, but a customer or external agent does not discover or select them.

Natural-language queries use the same persisted session router as the web app. Typed deterministic queries skip model interpretation, but still use the same identity, channel access, organisation scoping, and server-owned data binding.

What the assistant can do

AllowedNot available
List channels available to the signed-in userDiscover other tenants or organisations
Inspect a channel's queryable object and field schemaSelect internal products or relations
Ask a natural-language question through the canonical routerSelect arbitrary models, prompts, tools, or routing
Submit a typed records, aggregate, or saved-view intentSubmit raw SQL or override organisation scope
Read channel activity, members, and flat threadsDiscover an organisation-wide people directory through a channel
Publish an approved post, comment, or reaction with twin.writePublish internal reasoning or silent progress updates
Add an approved native record with twin.writeCreate source-backed rows or silently infer a write
Publish an approved view definition against its inspected versionOverwrite a newer view definition
Check a routed query and open an authenticated channel linkRead unrelated sessions, raw events, or model configuration
Submit feedback the user provided or confirmedInfer feedback or submit it without the user's knowledge

The recorded interface type—api, cli, or mcp—is audit metadata. It never grants authority or creates a separate execution policy.

Your other provider still matters

ChatGPT, Claude, Codex, or another provider receives the question and tool result under that provider's own data controls and retention terms. Twin access controls do not replace your organisation's review of that provider.

Who chooses the model

The connected assistant or end user does not select an arbitrary model for a Twin query. Model routes are configured for the deployment and evaluated for their intended tasks.

Keeping model routing server-side means an organisation can choose an approved model suited to the work, or move to another configured provider, without changing the public query contract. Cost, retention, capability, and quality remain part of the deployment decision.

Never share credentials in a prompt

Sign in through the protected browser screen. A support person or agent should never ask you to paste a token, client secret, password, cookie, SSH key, or Tailscale credential into a conversation.

On this page