July 24, 2024 — Cortex Guard for Snowflake Cortex AI — General Availability¶

We’re happy to announce the general availability of Cortex Guard for Snowflake Cortex AI, a new feature that enables enterprises to easily implement safeguards that filter out potentially inappropriate or unsafe large language model (LLM) responses. Cortex Guard introduces a new safety filter you can specify in a call to the COMPLETE function so that language model responses associated with harmful content - such as violent crimes, hate, sexual content, self-harm and more - are automatically filtered out. We are excited to introduce Cortex Guard, the next iteration of our gen AI platform, to help enterprises seamlessly introduce safety into the end-to-end gen AI application development process.

For details on how to use this feature, see Cortex Guard.