Dive into a collaborative space where members like YOU can exchange knowledge, tips, and best practices. Join the conversation today and unlock a wealth of collective wisdom to enhance your experience and drive success.
A practical case on using ai_query and ai_classify inside a Lakeflow Job to settle cases and prepare context before an agent runs. All data in this case is synthetic.TL;DRWe compared two designs on 47 planted cases, using the same model and the same ...
Persistent Memory Is Only the BeginningAs AI agents move from isolated conversations toward persistent workflows, memory is becoming part of enterprise AI infrastructure.An agent that remembers previous interactions can reduce repetitive instructions...
@ShenXu : I found this really interesting so did a bit of experimentation. My lab notes and a test notebook are available at https://medium.com/lab-notes/unity-catalog-functions-kept-ai-agents-from-acting-on-stale-memory-7d63e15f992b
Every serious data platform grows a dead-letter table, and it always becomes a graveyard. Here is how we turned one into a self-healing queue — without letting a language model anywhere near the warehouse.Every data platform that takes quality seriou...
Thanks for sharing, @KeerthiItigimat, what a great breakdown. How do you handle rules changing while rows are waiting in quarantine? Does remediation keep the original checks, use the latest approved rules, or run both?
DQX Studio already has its own documentation for the rule editor, the approval workflow, the scheduler. This is what running it against real pipelines, real approvers, and a growing quarantine table made us add on top of it — and around it. It'll be ...
Every serious data platform grows a dead-letter table, and it always becomes a graveyard. Here is how we turned one into a self-healing queue — without letting a language model anywhere near the warehouse.Every data platform that takes quality seriou...
I read about a team demo about their shiny new "autonomous AI agent” leadership. It queried databases, generated reports, sent Slack notifications—all hands-free. Impressive stuff.
Two weeks later? $12K in API costs, staging data accidentally pushed ...
This project, AgenticLakehouse, explores the cutting edge of "Agentic Data Analytics." I didn't just want a chatbot; I wanted a "living" interface for the Lakehouse. The result is a Multi-Agent System that intelligently orchestrates tasks, from query...
Tired of complex governance workflows? We’ve successfully combined the power of multi-agent AI with state-of-the-art orchestration tools to automate Databricks Unity Catalog (UC) access management!This isn’t just a basic script — it’s an intelligent,...