Governance and safety rules
Rules enforced in code, owned by named people.
Some limits no setting can change. Within them, your people set the policy, per project and action.
Never, by code
An AI employee never merges to the default branch, never deploys, and never changes Polis’s own settings.
Enforced in code, and no setting changes it.
Tier 1 · Safety rules
Five safety rules, on by default.
Only your Owner can switch one off, with step-up and a reason. A banner stays on every page while it is off, the change is audited, and a conformance report shows the state.
- 01 Never grant admin rights.
- 02 Never change Polis’s own accounts or any AI employee’s permissions.
- 03 Never remove the last admin.
- 04 Never create, read or rotate keys, tokens or passwords.
- 05 Never weaken protections Polis relies on.
Tier 2 · Access rules, and proof
Access rules per AI employee, and proof that the safety rules hold.
-
Tier 2 access rules
Access rules per AI employee.
-
Prove it
Polis attempts each safety violation and shows it refused.
People, policies and approvals
Named people decide, at the level you set.
-
Roles and two-factor authentication
Seven roles, two-factor authentication (TOTP) for every user, and step-up for sensitive actions.
-
Policy and approvals
Policies per project and action. Where a policy asks for approval, a named person decides and the decision is logged.
-
Autonomy per project
Autonomy is set per project: L0 · Advisory, L1 · Supervised, L2 · Autonomous. No AI employee runs above its project’s level, each employee can be capped lower, and approvals can be required for specific actions across the organisation.
-
Append-only audit
Every decision, approval, tool call and model call is recorded in an append-only audit log.
-
Pause all AI work
One switch pauses all AI work for everyone, and a banner shows it.
Limits and budgets
Every model call priced, every budget enforced.
-
Cost cap per task
A cost cap per task, per project.
-
Money budget
A global money budget with reservations. Every model call is priced and recorded, with no prompt or response content stored.
-
Per-employee limits
A cost cap per AI employee, and a limit on tasks per day.
After the pilot
Governance features we plan next.
-
Governance features
Groups, passkeys, approvals management, and audit export with hash chaining.
Book a demo
See it on your own workflow.
A 30-minute call: about 15 minutes of live product, including the pause-all switch, then your questions. Bring your CISO if you like.
What we show
- Roles that can’t overreach, with step-up for sensitive actions
- A model provider locked to a data class
- Approvals by a named person, in Slack or the panel
- The pause-all switch