On the radar·Unity Gateway·since 2026 Beta

Service policies for AI securables

Policies evaluated when a model is called and when it answers, returning allow, deny or ask, with built-in safety judges.

Why it is worth watching

The replacement for AI guardrails, and it fails closed by design.

What Beta promises

Open to most customers but not for production: support runs through engineering, and the shape of it can still move. On by default on Premium, off on Enterprise.

Who can use itMost customers
Production useNo
SupportEngineering only
On by defaultPremium yes, Enterprise no

The definitions are Databricks' own, on its release types page. The label on this page is the one the feature's documentation states, last checked on 14 Sept 2026.

Where to read more

We wrote it up: Guardrails for generative applications — Policies evaluated on the way in and on the way out of a model call, returning allow, deny or ask, plus the data-side masking that stops a prompt carrying what it should not. That page carries the Beta label while this entry does.

The Databricks documentation for Service policies for AI securables

Newsletter

Hear when Service policies for AI securables changes label

We re-read the documentation behind every preview and tell you when a label moves, or when a feature quietly disappears.

Choose what you get5 of 15

Each one is a section of the letter, and you only get the ones you tick. Every email carries a link back to this list, so you can change it later without an account.

Double opt-in: we send one email to check the address is yours. Nothing else until you confirm.