I ran the same 24 coding tasks through three arms: fixed Haiku, fixed Opus and Databricks-managed selection. The managed-selection arm passed all 24 tasks. Its 24 routing records also said task profiling was unavailable.That is not a contradiction. T...
Suppose a RAG application returns this:{ "response": "You can return the item within 90 days.", "citations": ["returns-policy"] }The cited document allows returns within 30 days.A citation-presence check should pass this response. A check that th...
Data Engineering 1.0 was largely about integrating, moving, consolidating massive data to support enterprise decisions. Enterprises built ETL pipelines, data warehouses, data lakes and orchestration platforms to bring data together reliably. Data Eng...
Promo Genie: Turning Trade-Promotion Data into Actionable DecisionsPromo Genie is a Databricks-native trade-promotion intelligence application built for Bisky Delight, a fictional FMCG biscuit brand. It combines governed Lakehouse data with a Genie A...
The OLTP architecture your agentic systems actually need, and how it compares to Supabase, Azure PostgreSQL, and Cosmos DBEarlier this year, Nikita Shamgunov — the engineer leading Databricks Lakebase — published a number that reframed my entire arch...
Building an Incremental Customer Data Migration Workflow in DatabricksBy Naveen AyallaIntroductionIn many enterprise environments, customer data is spread across legacy systems that were originally designed for operational processing rather than mode...
Great write-up, Naveen. Very practical and clear.I really like how you focused not just on migration, but on building a reliable incremental workflow with proper duplicate handling and governance. That’s where real value comes from.Also, connecting D...
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 ...
https://medium.com/@bijumathewt/real-world-langgraph-crewai-application-intelligent-databricks-alert-system-with-ai-7ba36e23f7a2You will love above article
Many enterprises today launch AI agents with high hopes but more often than not, those pilots never reach production. The culprit? Complexity, poor evaluations, ballooning costs, and governance gaps.Why do so many AI agent pilots never make it to pro...
Agent Bricks looks solid for scaling AI, and I’ve seen platforms like Agentra.io also tackle the enterprise workflow side of this challenge.
