AI ProvidersAvailable

Use Anthropic safely from the Assistant.

Claude models for long-context, instruction-following tasks. Route Anthropic model usage through governed Assistant workflows. Every read and write runs through a governed connection — scoped to what you allow, approved where it matters, and fully audited.

Capabilities

What the Assistant can do with Anthropic.

The top read and write actions, in plain language — each one a scoped action through a governed connection.

01
Read
Use Anthropic for drafting, reasoning, and extraction inside the Assistant.
02
Act
Keep model usage inside your governance boundary — every call audited.
03
Act
Apply company controls to which teams can reach Anthropic.

Example workflows

Put Anthropic to work.

Concrete ways teams use the Assistant with this tool — always inside the permission model.

001
Route approved model usage through company controls
The Assistant handles this through a governed Anthropic connection — scoped to your role and audit-logged.
002
Keep prompts and outputs inside your governance boundary
The Assistant handles this through a governed Anthropic connection — scoped to your role and audit-logged.
003
Track and audit AI usage across teams
The Assistant handles this through a governed Anthropic connection — scoped to your role and audit-logged.

Controls

Connected, but never unguarded.

Connecting Anthropic doesn't hand the Assistant the keys. Admins decide exactly what it can reach and do.

01
Permissions & scopes
Choose the exact read and write actions Anthropic exposes to the Assistant — nothing is implicit.
02
Approval for sensitive writes
Require a human to sign off before the Assistant changes records, sends messages, or moves money.
03
Audit logging
Every action against Anthropic is recorded — who, what, and when — for full accountability.

Connection detail preview

Anthropic governance controls

Available

Enabled actions

Govern model access by role
Audit prompts and outputs
Use approved providers in skills

Credential status

Stored in Vault, decrypted only at run time

Approval policy

Sensitive writes can require human sign-off

Audit trail

Every read, write, actor, and timestamp is logged

Govern Anthropic through Connections

Connect Anthropic once, set its scopes and approvals, and the Assistant can use it across the company — every action audit-logged.

See the Assistant use Anthropic safely.

Book a demo and we'll show the Assistant connected — and governed — on your own tools.