Databricksters
Subscribe
Sign in
Home
Podcast
Notes
Chat
AI & ML
Data Engineering
Archive
About
Latest
Top
Discussions
Your Low-Code Shortcut to Production-Grade Agent on Databricks
Watch now (16 mins) | Follow our end-to-end journey building a knowledge assistant with AgentBricks and establishing a continuous evaluation loop with…
Nov 18
•
Canadian Data Guy
and
Veena
3
16:25
The Goldilocks Approach: Hierarchical Classification with AI_QUERY in Databricks
Leverage Databricks `AI_QUERY` to tackle complex, context-dependent hierarchical classification problems that traditional ML and simple LLM prompts…
Nov 11
•
Mandy Baker
6
10 Lessons from Analyzing and Tuning Two Dozen Databricks SQL Warehouses
How to cut cost and boost performance
Nov 7
•
Artem Chebotko
3
2
Warming Up Databricks SQL Disk Cache for Reliable BI Dashboard Benchmarking
Ever benchmarked Databricks SQL and wondered why results fluctuate between runs? It’s often not your queries — it’s the cache.In my latest post, I walk…
Nov 4
•
Artem Chebotko
10
Integrate Teams with Genie using Azure Serverless Framework in 30mins!
A Teams Bot that integrates with Databricks Genie using conversational APIs, allowing users to query and interact with their data directly from Teams.
Nov 4
•
Ambarish
5
5
October 2025
Integrate Slack with Genie natively using Databricks Apps in 30mins!
Integrate Slack with Genie natively using Databricks Apps in 30min!
Oct 27
•
Ambarish
3
5
1
Getting Medieval on Token Costs
A Lakebase Powered Solution to Token-Based Rate Limiting
Oct 24
•
Austin
2
September 2025
How Liquid Clustering Improves Streaming Merges and P99 Latency
Watch now | The Trio Behind Simpler Streaming Merges: Deletion Vectors, Row-Level Concurrency, and Liquid Clustering
Sep 16
•
Canadian Data Guy
9
1
8:59
Agents are like onions (they have layers)
Using custom scorers to investigate spans within a trace in MLflow 3+.
Sep 3
•
Veena
5
August 2025
Doctors HATE this one dependency trick!
A quick guide to dependency management for machine learning using MLflow 3+.
Aug 19
•
Veena
7
1
Bayes’d and Redpilled
Markov Chain Monte Carlo Sampling using PyMC on Databricks
Aug 12
•
Austin
4
Beyond the Pipeline: The Blueprint for Enterprise AI Platforms using Databricks
Moving past dependency hell requires more than code—it demands a shift to a govern-first architecture.
Aug 5
•
Debu Sinha
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts