@anthu
Thoughts, stories and ideas.
Feb 17 · 7 min read · In Part 1 I connected OpenClaw to Snowflake Cortex as the LLM backend. Enterprise-grade security, unified billing, data stays in Snowflake. So far so good. But after running it for a while I noticed something: most of the tokens OpenClaw burns throug...
Join discussion
Feb 17 · 6 min read · I've been playing around with OpenClaw - an open-source AI assistant framework - and wanted to hook it up to Snowflake's Cortex LLM API. The idea: use enterprise-grade models like Claude Sonnet 4.5 through Snowflake's infrastructure while keeping my ...
Join discussion
Jan 13 · 4 min read · I've always been a fan of Snowflake's INFER_SCHEMA() function. Not only because it saves you from manually typing out column definitions but the whole idea of letting Snowflake figure out your schema from actual data feels like the right level of aut...
Join discussion
Jan 13 · 5 min read · I get asked about this a lot. Someone lands JSON from a REST API into a VARIANT column, and now they want proper columns without manually writing json_data:field1::VARCHAR, json_data:field2::NUMBER for every single path. And you guessed it - there's ...
Join discussion
Jan 10, 2022 · 1 min read · Having a lot of uniform data you might want to introduce some jitter to the data visualization. Most of the tutorials would suggest to use a random number and apply it to an axis to offset the visualistion point a bit. So far so good. Tableau for spe...
Join discussion