Secure by default.
Anrie only uses Slack conversations where it has been added, keeps credentials out of chat and model prompts, and never uses customer data to train models.
Slack bot membership scopes context.
Private Slack work stays out of public channel context.
Your content is used to provide Anrie, not train models.
Connected account credentials stay server-side.
Launch and spend wait for review.
Compliance
Security review materials.
Independently audited. Continuously verified.
AI safety
Controls for the risks that matter.
Slack scope, private conversations, model training, credentials, and sensitive actions each have a separate control.
Security control
Anrie only reads channels where it is added
Risk
A Slack install should not turn the whole workspace into agent context.
Control
Anrie uses Slack conversations only in channels where the bot is a member. Channels where it has not been added stay outside Anrie.
Documentation