Author: Kevin
-
LLM Patterns for SQL Generation: Teaching AI to Write Queries That Don’t Make You Cry
AI-generated SQL is everywhere now — especially inside Snowflake.But let’s be honest: sometimes AI writes queries with the same confidence (and accuracy) as Vanilla Ice claiming he didn’t sample Queen. If you want accurate, reliable SQL from LLMs, you need structure. Not vibes. Not hope. Actual Patterns. The kind of repeatable patterns that keep Snowflake…
-
The Art of AI-Assisted Query Tuning: When Your SQL Needs a Little… Persuasion
If the last post was about using AI to argue with your SQL, this one is about using AI to negotiate with it — the way JR Ewing negotiated: confidently, with a smirk, and fully prepared to expose what someone doesn’t want you to see. Welcome to the next chapter in this Snowflake + AI…
-
Let the Machines Argue: AI Query Validation in Snowflake (Part 2)
If Part 1 was about building trust, Part 2 is about giving your AI coworkers permission to bicker — productively. Because if “trust, but verify” was the Cold War version of collaboration, “let the machines argue” is the modern data equivalent. You don’t want a single all-knowing LLM nodding along; you want a tiny debate…
-
AI Query Validation — Because “Trust, But Verify” Isn’t Just for Cold War Spies
Part 1: Why AI-Validated Queries Are the New Data Governance Somewhere between a DBA whispering “it worked on my dev box” and an analyst insisting “the dashboard’s fine, I swear,” lies the truth — and usually, a join that went awkwardly wrong. In the age of AI, we’re generating queries faster than ever… and making…
-
Natural Language SQL: Talk to Your Data Like It’s 1999
You’ve been there. It’s late. You’re staring at a massive SQL query that looks like someone dropped a Scrabble board into a blender. You just wanted the top few customers by region, not an existential crisis. Enter Snowflake Cortex, where SQL meets AI and suddenly you can talk to your data like it’s your friendly…
-
Prompt Engineering Inside Snowflake: The Encore
When Prompts, Pipelines, and Power Ballads Collide By now, you’ve probably seen Snowflake Cortex do its parlor tricks — summarize data, classify text, maybe even generate haikus about ETL jobs. But let’s be honest: one-liners are fun; real orchestration is where it starts to sound like Led Zeppelin. In this encore, we’re chaining prompts, tuning…
-
Prompt Engineering Inside Snowflake: Tuning AI for Performance and Personality
Welcome back to our Snowflake + AI series, where we’ve been peeling back the layers of how prompt engineering actually works inside your data warehouse. Today, we’re getting hands-on — tuning the knobs that shape how your AI sounds, behaves, and sometimes… argues with you. Because just like a guitar amp, an AI model in…
-
Data-Driven AI in Snowflake: Feeding LLMs Without Losing Control
If you’ve been experimenting with Snowflake Cortex or external LLM calls, you’ve probably hit that moment when your prompts start pulling data dynamically… and your results get a little odd. One day, it’s spitting out perfect business summaries.The next day, it’s writing fan fiction about your sales metrics. Welcome to the messy middle — where…
-
Reusable Prompts in Snowflake: Building Templates That Actually Rock
If your first foray into AI inside Snowflake felt like a garage band session — noisy, creative, but a little out of tune — you’re not alone. Most data engineers start by hardcoding prompts in their SQL or Python scripts, quickly realizing they’ve got eighteen slightly different versions of “summarize this data” scattered across their…
-
Prompt Engineering Inside Snowflake: Data, AI, and a Little Bit of Rock ‘n’ Roll
If you’ve been living under a data warehouse, here’s your wake-up call: AI is moving into Snowflake, and prompt engineering is the backstage pass. Forget “build once, run everywhere.” We’re in the “train once, prompt forever” era — and Snowflake’s native integration with LLMs means your data can finally stop waiting for its turn on…