Cortex Code stopped being “just another AI feature” the moment skills landed. In under three months they’ve become the missing glue: portable, versioned building blocks that turn NPO data stacks into repeatable agent workflows.
Anthropic is scrambling for GPUs, AMD is finally shipping drop‑in AI cards, and Zyphra just proved you can train real models on a full AMD stack. All of that lands in your Snowflake account the moment you run create compute pool
Build-vs-buy got rewritten by agentic coding. So I retired the legacy BI tool. 😎
Generate XLSX files directly from Snowflake using a small Snowpark stored procedure, writing straight to a stage so stakeholders get ready-to-use Excel workbooks without any CSV exports or manual conversions
Snowflake’s interactive warehouses sit in a sweet spot for user-facing workloads: they cost 60% of a same-sized standard warehouse, can stay warm across business hours, and still serve sub‑second lookups from an interactive table
Claude Code and Snowflake's Cortex Code turn out to be the same agent wearing different hats - and that's exactly what makes them worth combining. A filesystem handoff between two AI agents replaced hours of manual Snowsight clicking.
Snowflake’s ACCOUNT_USAGE is powerful but often too complex. I built a cost analyst with Snowflake Intelligence: 19+ views merged into 6 tables, 25 billing rules, enabling questions like “why did costs spike?”
Using dlt’s AI workbench and Claude Code, I reverse‑engineered our ERP's undocumented 1,200+ table schema and produced an annotated DBML model plus ontology.
A PII-safe alternative to Brave web search for Snowflake Cortex Agents, using Perplexity and AI_REDACT
Snowflake tasks are great... until one stops running and nobody notices.
Taking Snowflake Cortex Code for a spin
Own your data: A simple, almost-free first‑party tracking stack