- 196 Views
- 1 replies
- 1 kudos
Enterprise AI Has a Serious Context Problem
After coming back from the Databricks Data + AI Summit this year, one thought has stayed with me. I keep hearing Databricks co-founder and CEO Ali Ghodsi talk about something that I am also starting to see in my own Data + AI POCs.For most enterprise...
- 196 Views
- 1 replies
- 1 kudos
- 1 kudos
Great post. I agree with the diagnosis, but I'm not sure the problem is new. I think agents are just making it visible.We've always had this gap. It was the gap between a junior and a senior engineer. A junior can know the tools very well. But a seni...
- 1 kudos
- 1176 Views
- 5 replies
- 6 kudos
5 Minute Features - a new video series
I have spent the past couple of months building up a small hobby YouTube project where I run through Databricks Features in an easy to digest format.I am for a very hands-on and demo heavy approach so you can actually see what is going on, and how th...
- 1176 Views
- 5 replies
- 6 kudos
- 6 kudos
I have neglected to update this feed - but lots of new 5 Minute Features have been released since the last post - along with an updated visual identity!Check them out here!https://www.youtube.com/watch?v=a9K8zTYS3_E&list=PLgYSYYgV-q4GgL-djRTC_2HFV5nc...
- 6 kudos
- 105 Views
- 0 replies
- 0 kudos
Check my blog on Databricks Unity Catalog
Struggling with a legacy Hive Metastore? I published a deep dive on modernizing your Data Governance on Databricks. Read how we executed a Unity Catalog migration for a complex, multi-tenant enterprise without disrupting daily business operations.htt...
- 105 Views
- 0 replies
- 0 kudos
- 201 Views
- 1 replies
- 1 kudos
Building Custom Agents on Databricks:LangGraph, Atlan-Grounded Routing, and Per-Run Cost with MLflow
The problem: rethinking routing in multi-agent systems on DatabricksDatabricks native supervisor agent pattern is a solid default for orchestrating multiple Genie spaces and tools but it comes with a routing constraint worth examining. The superviso...
- 201 Views
- 1 replies
- 1 kudos
- 1 kudos
@lina6556563 thank you, really interesting approach. Especially the combination of metadata-grounded routing with MLflow tracing.One thing I'd be curious to explore further is how routing behaves when the conversation gradually shifts domain. It migh...
- 1 kudos
- 4499 Views
- 1 replies
- 2 kudos
Databricks CustomerLake
Databricks CustomerLake: Inside the Agentic CDP Built for the Age of AIA deep dive into what CustomerLake actually is, how it works, and what it looks like in practice.At Data + AI Summit 2026, Databricks announced CustomerLake — an Agentic Customer ...
- 4499 Views
- 1 replies
- 2 kudos
- 2 kudos
can I get hands-on with this platform?
- 2 kudos
- 109 Views
- 0 replies
- 0 kudos
Genie Ontology na prática
Databricks - Genie Ontology 吏 Se "receita" significa uma coisa para Vendas, outra para o Financeiro e uma terceira no ERP, o seu agente de IA vai escolher uma sozinho. E vai responder com a mesma confiança nos três casos.É esse o problema que o Geni...
- 109 Views
- 0 replies
- 0 kudos
- 157 Views
- 0 replies
- 0 kudos
Property & Casualty Insurance Lakehouse
When building a Property & Casualty Insurance Lakehouse, one of the first things to understand is:A Claim is not just a Claim Amount.Consider a simple auto claim.At different points in the lifecycle, the same claim might have:Indemnity Reserve = $15,...
- 157 Views
- 0 replies
- 0 kudos
- 227 Views
- 0 replies
- 0 kudos
DQX - Everything The Docs Don’t Say Yet
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 ...
- 227 Views
- 0 replies
- 0 kudos
- 150 Views
- 0 replies
- 1 kudos
Unmasking the Connected Consumer
Behind every clean “Golden Record” is a messy web of shared emails, phones, and legacy IDs. Here’s how we turned that web into an interactive, cluster-aware graph a data steward can actually work with — built on Streamlit, NetworkX, and a Databricks ...
- 150 Views
- 0 replies
- 1 kudos
- 86 Views
- 0 replies
- 0 kudos
Agent Proposes, DQX Disposes
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...
- 86 Views
- 0 replies
- 0 kudos
- 177 Views
- 0 replies
- 0 kudos
How to force Databricks Serverless to process 1 TB (40 Billion Rows) in 14 Minutes
Databricks Serverless is incredible for abstracting infrastructure, but because it scales based on the volume of pending tasks, relying on default configurations for massive data ingestion can leave performance on the table.I recently ran an experime...
- 177 Views
- 0 replies
- 0 kudos
- 212 Views
- 1 replies
- 3 kudos
I Built an AI-Powered Data Pipeline Generator for Databricks — Here Is What Happened
Building robust Medallion architectures takes time. Writing the same boilerplate for Auto Loader, streaming tables, and SCD Type 2 merges across different projects is a bottleneck.So, I ran an experiment: What happens if you let AI write your Spark D...
- 212 Views
- 1 replies
- 3 kudos
- 3 kudos
excellent work
- 3 kudos
- 1266 Views
- 2 replies
- 2 kudos
Databricks as a Semantic Engine: Why the Semantic Layer Was Never Enough
For twenty years, the semantic layer has been the industry's answer to a simple question: how do we make sure everyone means the same thing when they say "revenue"? And for twenty years, the answer has mostly failed. Not because the idea was wrong, b...
- 1266 Views
- 2 replies
- 2 kudos
- 2 kudos
Thank you for this really helpful article. Since I'm about to start building our Databricks environment and need to account for this semantic "engine" could you refer me to more helpful articles like this?
- 2 kudos
- 2436 Views
- 1 replies
- 4 kudos
From SSIS to Databricks: Accelerating ETL Modernization with AI-Powered Utility
As enterprises race toward cloud-native data platforms, modernising legacy ETL pipelines remains one of the most persistent bottlenecks. For organizations that have relied on SQL Server Integration Services (SSIS) for years, rewriting hundreds of pac...
- 2436 Views
- 1 replies
- 4 kudos
- 4 kudos
where is the details of utilities
- 4 kudos
- 153 Views
- 0 replies
- 1 kudos
From Data Quality to Context Quality
High Quality Data is no longer enough for AI based decisions. Governance, Lineage and Observability helped creation of Trusted Data Products to allow consumers to use the trusted information delivered by the Data Platforms.Generative AI and Agentic A...
- 153 Views
- 0 replies
- 1 kudos
| User | Count |
|---|---|
| 85 | |
| 76 | |
| 73 | |
| 60 | |
| 43 |
