Sherpa of Data

Author: Kevin

  • Natural Language SQL: Talk to Your Data Like It’s 1999

    —

    by

    Kevin
    in

    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

    —

    by

    Kevin
    in

    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

    —

    by

    Kevin
    in ,

    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

    —

    by

    Kevin
    in ,

    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

    —

    by

    Kevin
    in ,

    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

    —

    by

    Kevin
    in ,

    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…

  • The Intelligent Data Warehouse — How Snowflake Meets AI

    —

    by

    Kevin
    in ,

    …and right now, the same goes for AI in your data stack. For the last decade, everyone has been talking about “data-driven decision-making” as if it were some new religion. The problem? Most warehouses still act like a library from 1999. You can borrow the books, but heaven forbid you ask them to summarize themselves.…

  • Complete Guide to Snowflake’s Tag-Based Masking (Now With Auto-Tagging)

    Complete Guide to Snowflake’s Tag-Based Masking (Now With Auto-Tagging)

    —

    by

    Kevin
    in

    IntroductionIf you’ve followed our site for a while, you would have seen in a previous post how powerful tag-based masking policies are in Snowflake. They let you enforce consistent data masking rules across columns without constantly rewriting logic. But Snowflake hasn’t stopped there—recent enhancements now make it even easier to classify, tag, and mask data…

  • Level Up Your Snowflake Dashboard: Filters Making Audits Less Sucky

    —

    by

    Kevin
    in

    Snowflake Dashboards can do a lot more than just show pretty numbers. Today, let’s focus on something that every data pro eventually has to deal with—filters that make navigating your dashboards less painful, especially when it comes to everyone’s favorite task: AUDITING. Ah yes, auditing—because nothing says “data dream job” like tracing permissions. Whether it’s…

  • Making Snowflake Flow Better: Cleaner Queries

    —

    by

    Kevin
    in

    In a recent Snowflake release, a slick new operator quietly entered the scene: ->>. This little guy can make certain query workflows both more readable and more efficient—especially when you’re dealing with multi-step commands like SHOW, LIST, or DESCRIBE. The Classic Way: RESULT_SCAN(LAST_QUERY_ID(-1)) You may already be familiar with the pattern below: Effective? Sure. Readable?…