Building a Semantic AI Layer in Snowflake: From Metrics to AI Insights
summary
Demo shows Snowflake running Cortex AI functions (complete, search, classify, summarize) over ingested CSVs to build a semantic YAML model, load data into tables, and expose answers plus the generated SQL. Claim: semantic model takes ~15 minutes, app integration under 20 minutes; proof: a Streamlit UI and an agent query run end-to-end against Snowflake (no data movement), verified-query logging and RBAC applied. Results return aggregates, SQL, and monitored query history.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:49Snowflake architecture
- 11:42Traditional data access challenges
- 13:07Snowflake Cortex AI
- 23:21Cortex AI functions deep dive
- 35:07Hands-on lab setup
- 55:06Semantic models with Cortex Analyst
- 1:07:22Verified queries and monitoring
- 1:10:31Conclusion and Q&A
related talks
30mBuilding Data AI Application with the Snowflake AI Data Cloud
29mBuilding End to End Gen AI Powered Analytics: From Data to Production
17mPrepare to master common generative AI use cases with ease
23mAcceleratinag Data Science and Machine Learning with Snowflake DataTech
15mEnterprise AI Runs on Trusted Data
56mDeveloping AI Applications with SQL AI: Ground to Cloud to Fabric
01h 18mFrom raw data to interactive data app in an hour
27mUsing GenAI with Audio Data for Driving Better Customer Experience