Notion AI

Description Permissions Security & Compliance

Notion AI finds the information you need by searching across your Notion workspace and Slack. It helps you summarize threads, find next steps, and pull in relevant context, right where you work.Coming soon: Notion Custom Agents will answer your questions directly in Slack and streamline your work. Want early access? Fill out this form and let us know you’d like to test Notion Custom Agents with Slack: https://notion.notion.site/26fefdeead05803ca7a6cd2cdd7d112fNote: Notion AI answers are generated using LLMs like GPT-5 and Claude. You should double-check all answers for accuracy. To learn more about the Notion AI Connector for Slack, visit our documentation here: https://www.notion.com/help/notion-ai-connectors-for-slackNote: Notion AI app for Slack uses Slack’s Real-time Search API for keyword search and semantic search functionality.

Permissions

Notion AI will be able to view:

Notion AI will be able to do:

Review the details to better understand this app’s security practices. To learn more about assessing apps for your workspace visit our Help Center.

General

Privacy & data governance

Data retention policy

Slack content is stored as embeddings using vector databases like Turbopuffer. These embeddings allow for efficient searches and comparisons across different pieces of text to provide accurate and relevant responses to your questions. Notion’s vector databases have been reviewed by our Security team and independently assessed by an external auditor as part of our SOC 2 Type II attestations. See https://www.notion.com/help/notion-ai-security-practices for more information.

Data archiving and removal policy

Notion treats your Slack content with the privacy principle of data minimization in mind. If you decide to disconnect your Slack environment from Notion AI, your Slack content will become unsearchable, and we will begin deleting any data that is stored.

Data storage policy

Slack content is stored as embeddings using vector databases like Turbopuffer. These embeddings allow for efficient searches and comparisons across different pieces of text to provide accurate and relevant responses to your questions. Notion’s vector databases have been vetted by our Security team as well as by an external auditor to obtain their SOC2 Type II attestations. For specific locations, please refer to this link: https://notion.notion.site/Notion-s-List-of-Subprocessors-268fa5bcfa0f46b6bc29436b21676734?pvs=74

App/service has sub-processors

yes

Guidelines for sub-processors

https://notion.notion.site/Notion-s-List-of-Subprocessors-268fa5bcfa0f46b6bc29436b21676734?pvs=74

App/service uses large language models (LLM)

yes

LLM model(s) used

Open AI models, Anthropic models

LLM retention settings

When using Notion AI, our LLM providers utilize zero data retention, so no data is stored with LLM providers.

LLM data tenancy policy

Notion AI uses LLMs both on Notion‑hosted infrastructure and via third‑party providers, with any data sent to provider‑hosted models transmitted through their APIs. please refer to the list of subprohttps://www.notion.com/help/notion-ai-security-practices

LLM data residency policy

Regarding data residency around our LLMs, please refer to the list of subprocessors here for the most updated list and locations: https://www.notion.com/help/notion-ai-security-practices

Certifications & compliance

Security