TechPrufer
Get started
Databricks
Databricks logoDatabricks · Feature trail

Conversational Data Access

12 posts · Jul 2026 – Oct 2026

What this trail covers

This post details new features for Databricks Genie, enhancing its conversational data access capabilities. It focuses on turning insights derived from natural language queries into actionable steps within the Databricks platform. This likely involves new integrations or workflows that allow users to not only retrieve data but also initiate actions or processes based on that data, further abstracting complexity and empowering users to act on information directly. S&P Global Energy leveraged Geni

All Databricks trails
  1. AI-powered analytics: Building data visualizations with natural language vs. SQLThis post details how Databricks Genie is being enhanced to provide more trustworthy answers for users by grounding natural language queries in semantic context. It describes the technical challenges of generating reliable visualizations from natural language and outlines how semantic grounding, coupled with good governance, addresses these issues. The post highlights the importance of conversational threads and how Genie is being integrated into everyday tools with built-in governance to deliver on the promise of natural-language analytics.
  2. How Genie Ontology powers product development at DatabricksThis post details how the Genie Ontology is being used to power product development at Databricks. It explains how users can run adoption reviews with simple prompts, how Genie finds the right data, and how users can review Genie's citations. It also covers asking follow-up questions to forecast trends, scheduling workflows, and turning conversations into shareable agents. This contributes to the Conversational Data Access capability by demonstrating how natural language interactions can be leveraged to drive product development workflows and create reusable AI agents.
  3. How to choose your first Genie Agents for maximum impactThis post provides guidance on selecting the initial Genie Agents for maximum impact, focusing on identifying workflows that are suitable for agentic automation and offer significant business value. It introduces a rubric for evaluating potential agent candidates and discusses common pitfalls to avoid during the selection process, emphasizing the importance of starting with well-defined, high-impact use cases.
  4. Connecting customer context to measurable ROI with agentic marketingThis post details how Databricks Genie is being extended to support agentic marketing workflows. It introduces the concept of using identity resolution to connect customer context to measurable ROI, leveraging a Customer Data Platform (CDP) that is embedded within Databricks. The CDP acts as a governed action layer, allowing AI agents to translate insights derived from customer data into concrete marketing actions. The post discusses the importance of measurement and attribution in this agentic model, implying new capabilities or approaches for tracking the effectiveness of AI-driven marketing campaigns. This represents an evolution of conversational data access by enabling agents to not only retrieve data but also to act upon it in a governed and measurable way within a marketing context.
  5. From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCPThis post details how S&P Global Energy partnered with Databricks to transform their structured data estate into a conversational interface using Databricks Genie Agents and the Model Catalog Platform (MCP). The core technical challenge was enabling natural language interaction with complex, domain-specific energy data. This was achieved by developing custom agents that understand energy terminology and can translate natural language queries into executable Spark SQL. The process involved fine-tuning LLMs on domain-specific data, building robust prompt engineering strategies, and integrating with the Databricks SQL engine for query execution. The outcome is a system that democratizes data access, allowing users to query vast datasets conversationally, thereby accelerating insights and decision-making within the energy sector.
  7. Genie One MCP: Give any AI Agent the Right Business ContextThis post introduces "Genie One MCP" (Model Context Provider), a new capability for Databricks Genie that provides AI agents with the right business context. It details how Genie can now access and interpret business context from various sources, such as Databricks SQL, tables, and external knowledge bases, to inform AI agent actions. The post highlights the technical implementation of integrating these context sources into the agent's reasoning process, enabling agents to perform more sophisticated tasks like generating reports, performing analyses, and making data-driven decisions. It emphasizes the ability to provide agents with specific business context, moving beyond generic information retrieval.
  8. Unity Catalog Pages: a governed home for your business knowledge in Genie OntologyThis post details the integration of Unity Catalog Pages into Databricks Genie, enabling a governed home for business knowledge. It describes how Genie can now leverage the Unity Catalog to understand and query data through natural language, turning insights into actionable steps. This enhances conversational data access by providing a structured and governed way for users, including marketers, to interact with their data and knowledge base.
  9. How energy teams turn theft detection into governed action with Genie and AI business processesThis post details how energy teams can leverage Databricks Genie and AI business processes to turn theft detection into governed action. It describes the integration of AI business processes with Genie's conversational interface, enabling users to move from identifying theft to taking concrete, governed actions. This involves using AI business processes to orchestrate actions based on detected theft, ensuring compliance and operational efficiency. The technical depth lies in how these AI business processes are designed and integrated to interact with Genie for actionable outcomes in theft detection scenarios.
  10. How Databricks’ marketers use data 3x more with Genie, an AI analytics assistantThis post details how Databricks' marketers are using Genie, an AI analytics assistant, to leverage data 3x more effectively. It highlights the practical application of Genie in enabling marketers to derive insights and take action from data through natural language queries, thereby increasing their data utilization and productivity.
  11. Beyond answers: New Genie One features to turn insights into actionThis post introduces new features for Databricks Genie that enable users to turn insights derived from natural language queries into actionable steps within the Databricks platform. This goes beyond simply answering questions to allowing users to initiate workflows and processes directly from their insights, enhancing the platform's utility for acting on data.
  12. Designing effective Genie Agents from a single promptThis post details how to design effective Genie Agents from a single prompt. It likely covers prompt engineering techniques, best practices for defining agent behavior and capabilities within a single prompt, and potentially strategies for evaluating and iterating on agent performance based on prompt design. This contributes to the conversational data access capability by providing a more streamlined and efficient method for agent creation.
  13. How Scottish Water Made Its Capital Investment Data Conversational With Databricks GenieThis post details how Scottish Water leveraged Databricks Genie to make their capital investment data conversational. It highlights the technical implementation of using natural language queries to access and derive insights from complex investment data, enabling better decision-making and operational efficiency. The focus is on the practical application of conversational AI for managing and understanding critical business data within the Databricks Lakehouse.
  14. How a major freight railroad scaled pipeline creation with Genie CodeThis post details how a major freight railroad scaled pipeline creation with Genie Code. It highlights the use of natural language prompts to generate code for data pipelines, significantly accelerating development time and enabling a broader range of users to contribute to data infrastructure. The focus is on the practical application of AI-powered code generation for a specific engineering task: building data pipelines.
  15. Convert proprietary code to open ANSI SQL with Genie CodeThis post details how Databricks Genie can convert proprietary code to open ANSI SQL. This capability likely involves advancements in natural language processing and code generation to translate complex, non-standard SQL dialects into their ANSI SQL equivalents, making data accessible and interoperable across different systems.