back_office_ops · saas · workflow
How Slack built Slack AI to be secure and private using RAG and AWS escrow VPC
The generative AI market lacked enterprise-grade security and privacy patterns, and Slack needed a way to leverage top-tier LLMs while guaranteeing customer data would never leave its trust boundary or be used for model training.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User invokes Slack AI
Only the user who invokes Slack AI can see the AI-generated output.
Tools used
Retrieval Augmented Generation (RAG)AWSLLMs
Outcome
Slack AI was built using RAG on LLMs hosted in an AWS escrow VPC, keeping all customer data within Slack's trust boundary. Ninety percent of users who adopted AI reported higher productivity.
Results
Volume90%
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes.
enterprise searchragsummarizationchat transcriptknowledge basemetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedsoftwareemployee productivitytechnical build writeupback office opsrag answering