Building Data AI Application with the Snowflake AI Data Cloud
summary
Company use case builds a customer-facing data+AI app on Snowflake for a fintech, keeping one copy of data and avoiding copies for Spark teams. Architecture uses Iceberg tables + open Polaris catalog, ingestion via Snowpipe and Snowpipe streaming (1–3s latency) from Kafka/Firehose, declarative pipelines (Snowflake dynamic/streaming tables) and containerized services running inside Snowflake. Adds Cortex Search for vector + text search and serverless fine‑tuning (large-model distill to smaller, cheaper models). Security includes BYOK, MFA, full auditing, 90‑day time travel and cross‑region replication.
AI-written summary · about
chapters (6)
- 0:00Introduction to Snowflake
- 7:19Snowflake AI architecture overview
- 16:39Data foundation with Iceberg
- 20:12Streaming and transformations
- 24:37Security and governance
- 28:14AI and application building
related talks
31mAI-driven DataOps: Building data products with a taste of the future
23mAcceleratinag Data Science and Machine Learning with Snowflake DataTech
01h 17mData Engineering in the AI Era: Building a Robust Foundation for AI Applications
15mEnterprise AI Runs on Trusted Data
01h 13mBuilding a Semantic AI Layer in Snowflake: From Metrics to AI Insights
29mBuilding End to End Gen AI Powered Analytics: From Data to Production
04mMaximize enterprise AI with seamless interoperability
27mAgile Data Platforms : Innovate at the speed of thought