Databricks Community

Brahmareddy

A pipeline change can run successfully and still ship wrong data: a join that duplicates rows, a filter that moves a revenue total by a few percent. With AI agents now writing more pipeline code, I wanted a check that runs before a change reaches pro...

Brahmareddy

Databricks Agent Memory brings an interesting new direction to building AI agents that can learn from past interactions.Recently, Databricks introduced Agent Memory, and I think this is an interesting step toward making AI agents more useful in every...

Brahmareddy

I have been working with Python, PySpark, and SQL for years. But recently, while experimenting with Databricks Genie Code, I had a moment where I thought, "Are we entering a world where simple English becomes one of the most powerful programming lang...

Brahmareddy · 10-08-2026

AI is getting more powerful every day. But one question keeps coming back to my mind:Is enterprise data really ready to power AI?From my own data engineering work, I have seen that building pipelines, tables, dashboards, and reports is only one part ...

Brahmareddy · 09-24-2026

Over the last few years, I have spent a lot of time experimenting with one question: How do we turn Data + AI capabilities into applications people actually want to use?That curiosity led me to build multiple POCs and applications using Databricks + ...

Brahmareddy

Hi @DoTA, How are you doing today? Good catch, and you're right. I oversimplified in the post. The tool doesn't sum the raw hash, it casts it first:SUM(CAST(xxhash64(cols) AS DECIMAL(38, 0)))So there's no overflow and no wrapping, and it works the sa...

Brahmareddy

Thanks, @DoTA DoTA. Really useful points, especially around memory scope and keeping business rules separate from agent memory.I agree that trusted business definitions should stay in the governed layer, while memory should focus on user preferences ...

Brahmareddy · 10-02-2026

Hi @juanlozadab , thanks for sharing this thoughtful perspective! Keeping Delta as the source of truth and choosing the serving layer based on the access pattern makes sense to me.For this project, I focused on getting the complete experience working...

Brahmareddy · 10-01-2026

Thanks, @juanlozadab jlb. I really appreciate you digging into the architecture and not just the demo.Keeping embeddings in Delta right next to the source tables was actually the part I went back and forth on most. It was tempting to reach for a dedi...

Brahmareddy · 09-25-2026

Thank you, @ThomazNeto. This is exactly the kind of input I was hoping to get.I really like the focus on the demo-to-production gap. Post-mortems, authentication and governance decisions, cost/latency, evaluation results, and deployable reference pro...

Databricks Community

User Stats

User Activity

Making AI-agent writes safe on Databricks: lineage, shallow clones, null-safe diffs, rollback

AI Agents Should Not Start Every Conversation From Zero

English Is Becoming a Powerful Programming Language in Databricks!

Is Enterprise Data Ready to Power AI?

From Databricks POCs to Building a Data + AI Community

Re: Making AI-agent writes safe on Databricks: lineage, shallow clones, null-safe diffs, rollback

Re: AI Agents Should Not Start Every Conversation From Zero

Re: Future of Movie Discovery: How I Built an AI Movie Recommendation Agent on Databricks Free Editi

Re: Future of Movie Discovery: How I Built an AI Movie Recommendation Agent on Databricks Free Editi

Re: From Databricks POCs to Building a Data + AI Community