<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: What is the core goal of your project or what problem are you trying to solve with generative AI in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140779#M1472</link>
    <description>&lt;DIV class="paragraph"&gt;
&lt;P&gt;Below are high-impact problems you can solve with Databricks and generative AI, grounded in your enterprise data and governed end to end.&lt;/P&gt;
&lt;P&gt;Customer and employee knowledge access&lt;BR /&gt;Build RAG-powered knowledge assistants that answer questions over your proprietary documents, wikis, PDFs, and data—accurate, safe, and continuously evaluated.&lt;/P&gt;
&lt;P&gt;Deploy customer support agents that find answers, summarize cases, and execute tasks, with integrated evaluation and guardrails to meet production quality bars.&lt;/P&gt;
&lt;P&gt;Provide natural-language data access for analysts and business users via LakehouseIQ, which learns your org’s jargon and usage patterns for better answers.&lt;/P&gt;
&lt;P&gt;Personalization and decisioning&lt;BR /&gt;Power structured RAG and real-time personalization by injecting user/account features (orders, status, risk) into prompts using Feature &amp;amp; Function Serving and online tables.&lt;/P&gt;
&lt;P&gt;Automate recommendations, pricing, routing, and next-best-actions by joining LLMs with governed, low-latency context from your lakehouse.&lt;/P&gt;
&lt;P&gt;Search and retrieval quality&lt;BR /&gt;Deliver high-recall, governed enterprise search with Vector Search: serverless indexing/sync from Delta tables, hybrid keyword+semantic retrieval, and UC-integrated ACLs.&lt;/P&gt;
&lt;P&gt;Improve retrieval with embedding model finetuning and reranking to boost downstream RAG accuracy on in-domain data.&lt;/P&gt;
&lt;P&gt;Document and content automation&lt;BR /&gt;Build document parsing/extraction pipelines (PDF/HTML) to convert unstructured content into structured fields for dashboards, QA, and downstream agents.&lt;/P&gt;
&lt;P&gt;Enable multimodal RAG to search and reason across text, images, and complex PDFs using multimodal embeddings and Vector Search.&lt;/P&gt;
&lt;P&gt;Governed deployment, evaluation, and monitoring&lt;BR /&gt;Enforce unified governance (access, lineage, auditing, sharing) across data, models, tools, and agents with Unity Catalog—no bolt‑on silos.&lt;/P&gt;
&lt;P&gt;Measure and improve quality with MLflow Evaluation and Agent Evaluation (LLM-as-a-judge, custom scorers), consistent offline→online assessment, and trace-level root cause analysis.&lt;/P&gt;
&lt;P&gt;Monitor production with AI Gateway-enabled inference tables to log requests/responses and join with usage and model details for observability and retraining loops.&lt;/P&gt;
&lt;P&gt;Build and optimize AI agents, fast&lt;BR /&gt;Use the Mosaic AI Agent Framework to iterate on RAG and tool-calling agents quickly—including evaluation loops, guardrails, and one-click serving from Unity Catalog.&lt;/P&gt;
&lt;P&gt;Prototype in AI Playground, author in code with MLflow ResponsesAgent, and deploy agents** to scalable Model Serving endpoints with credentials scoped by governance.&lt;/P&gt;
&lt;P&gt;Model strategy and customization&lt;BR /&gt;Start with high-quality open models like DBRX (fast MoE, strong on code and reasoning), or query external/managed models through Foundation Model APIs under unified governance.&lt;/P&gt;
&lt;P&gt;Fine-tune and adapt models to your domain with Mosaic AI Training and register/serve them in Unity Catalog to retain full control over weights and IP.&lt;/P&gt;
&lt;/DIV&gt;</description>
    <pubDate>Mon, 01 Dec 2025 19:13:28 GMT</pubDate>
    <dc:creator>iyashk-DB</dc:creator>
    <dc:date>2025-12-01T19:13:28Z</dc:date>
    <item>
      <title>What is the core goal of your project or what problem are you trying to solve with generative AI or</title>
      <link>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140694#M1466</link>
      <description>&lt;P&gt;What problem are you trying to solve using Databricks and generative AI?&lt;/P&gt;</description>
      <pubDate>Mon, 01 Dec 2025 07:33:34 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140694#M1466</guid>
      <dc:creator>Suheb</dc:creator>
      <dc:date>2025-12-01T07:33:34Z</dc:date>
    </item>
    <item>
      <title>Re: What is the core goal of your project or what problem are you trying to solve with generative AI</title>
      <link>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140770#M1469</link>
      <description>&lt;P&gt;This is quite a generic question. The answer really depends on the &lt;STRONG&gt;industry&lt;/STRONG&gt;, the &lt;STRONG&gt;type and quality of data available&lt;/STRONG&gt;, and the &lt;STRONG&gt;budget or constraints&lt;/STRONG&gt; for the solution.&lt;/P&gt;&lt;P&gt;Generative AI on Databricks can solve a wide range of problems, from text summarisation to code generation to intelligent searc, but the use case always varies by context.&lt;/P&gt;&lt;P&gt;Are you looking for something more specific?&lt;BR /&gt;If yes, could you share a bit more detail about:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;&lt;P&gt;your industry or domain&lt;/P&gt;&lt;/LI&gt;&lt;LI&gt;&lt;P&gt;the business problem you’re trying to address&lt;/P&gt;&lt;/LI&gt;&lt;LI&gt;&lt;P&gt;the data sources you have&lt;/P&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;That will help in giving a more accurate and helpful answer.&lt;/P&gt;</description>
      <pubDate>Mon, 01 Dec 2025 17:48:06 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140770#M1469</guid>
      <dc:creator>bianca_unifeye</dc:creator>
      <dc:date>2025-12-01T17:48:06Z</dc:date>
    </item>
    <item>
      <title>Re: What is the core goal of your project or what problem are you trying to solve with generative AI</title>
      <link>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140778#M1471</link>
      <description>&lt;DIV class="paragraph"&gt;
&lt;P&gt;Below are high-impact problems you can solve with Databricks and generative AI, grounded in your enterprise data and governed end to end.&lt;/P&gt;
&lt;P&gt;Customer and employee knowledge access&lt;BR /&gt;Build RAG-powered knowledge assistants that answer questions over your proprietary documents, wikis, PDFs, and data—accurate, safe, and continuously evaluated.&lt;/P&gt;
&lt;P&gt;Deploy customer support agents that find answers, summarize cases, and execute tasks, with integrated evaluation and guardrails to meet production quality bars.&lt;/P&gt;
&lt;P&gt;Provide natural-language data access for analysts and business users via LakehouseIQ, which learns your org’s jargon and usage patterns for better answers.&lt;/P&gt;
&lt;P&gt;Personalization and decisioning&lt;BR /&gt;Power structured RAG and real-time personalization by injecting user/account features (orders, status, risk) into prompts using Feature &amp;amp; Function Serving and online tables.&lt;/P&gt;
&lt;P&gt;Automate recommendations, pricing, routing, and next-best-actions by joining LLMs with governed, low-latency context from your lakehouse.&lt;/P&gt;
&lt;P&gt;Search and retrieval quality&lt;BR /&gt;Deliver high-recall, governed enterprise search with Vector Search: serverless indexing/sync from Delta tables, hybrid keyword+semantic retrieval, and UC-integrated ACLs.&lt;/P&gt;
&lt;P&gt;Improve retrieval with embedding model finetuning and reranking to boost downstream RAG accuracy on in-domain data.&lt;/P&gt;
&lt;P&gt;Document and content automation&lt;BR /&gt;Build document parsing/extraction pipelines (PDF/HTML) to convert unstructured content into structured fields for dashboards, QA, and downstream agents.&lt;/P&gt;
&lt;P&gt;Enable multimodal RAG to search and reason across text, images, and complex PDFs using multimodal embeddings and Vector Search.&lt;/P&gt;
&lt;P&gt;Governed deployment, evaluation, and monitoring&lt;BR /&gt;Enforce unified governance (access, lineage, auditing, sharing) across data, models, tools, and agents with Unity Catalog—no bolt‑on silos.&lt;/P&gt;
&lt;P&gt;Measure and improve quality with MLflow Evaluation and Agent Evaluation (LLM-as-a-judge, custom scorers), consistent offline→online assessment, and trace-level root cause analysis.&lt;/P&gt;
&lt;P&gt;Monitor production with AI Gateway-enabled inference tables to log requests/responses and join with usage and model details for observability and retraining loops.&lt;/P&gt;
&lt;P&gt;Build and optimize AI agents, fast&lt;BR /&gt;Use the Mosaic AI Agent Framework to iterate on RAG and tool-calling agents quickly—including evaluation loops, guardrails, and one-click serving from Unity Catalog.&lt;/P&gt;
&lt;P&gt;Prototype in AI Playground, author in code with MLflow ResponsesAgent, and deploy agents** to scalable Model Serving endpoints with credentials scoped by governance.&lt;/P&gt;
&lt;P&gt;Model strategy and customization&lt;BR /&gt;Start with high-quality open models like DBRX (fast MoE, strong on code and reasoning), or query external/managed models through Foundation Model APIs under unified governance.&lt;/P&gt;
&lt;P&gt;Fine-tune and adapt models to your domain with Mosaic AI Training and register/serve them in Unity Catalog to retain full control over weights and IP.&lt;/P&gt;
&lt;/DIV&gt;</description>
      <pubDate>Mon, 01 Dec 2025 19:13:25 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140778#M1471</guid>
      <dc:creator>iyashk-DB</dc:creator>
      <dc:date>2025-12-01T19:13:25Z</dc:date>
    </item>
    <item>
      <title>Re: What is the core goal of your project or what problem are you trying to solve with generative AI</title>
      <link>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140779#M1472</link>
      <description>&lt;DIV class="paragraph"&gt;
&lt;P&gt;Below are high-impact problems you can solve with Databricks and generative AI, grounded in your enterprise data and governed end to end.&lt;/P&gt;
&lt;P&gt;Customer and employee knowledge access&lt;BR /&gt;Build RAG-powered knowledge assistants that answer questions over your proprietary documents, wikis, PDFs, and data—accurate, safe, and continuously evaluated.&lt;/P&gt;
&lt;P&gt;Deploy customer support agents that find answers, summarize cases, and execute tasks, with integrated evaluation and guardrails to meet production quality bars.&lt;/P&gt;
&lt;P&gt;Provide natural-language data access for analysts and business users via LakehouseIQ, which learns your org’s jargon and usage patterns for better answers.&lt;/P&gt;
&lt;P&gt;Personalization and decisioning&lt;BR /&gt;Power structured RAG and real-time personalization by injecting user/account features (orders, status, risk) into prompts using Feature &amp;amp; Function Serving and online tables.&lt;/P&gt;
&lt;P&gt;Automate recommendations, pricing, routing, and next-best-actions by joining LLMs with governed, low-latency context from your lakehouse.&lt;/P&gt;
&lt;P&gt;Search and retrieval quality&lt;BR /&gt;Deliver high-recall, governed enterprise search with Vector Search: serverless indexing/sync from Delta tables, hybrid keyword+semantic retrieval, and UC-integrated ACLs.&lt;/P&gt;
&lt;P&gt;Improve retrieval with embedding model finetuning and reranking to boost downstream RAG accuracy on in-domain data.&lt;/P&gt;
&lt;P&gt;Document and content automation&lt;BR /&gt;Build document parsing/extraction pipelines (PDF/HTML) to convert unstructured content into structured fields for dashboards, QA, and downstream agents.&lt;/P&gt;
&lt;P&gt;Enable multimodal RAG to search and reason across text, images, and complex PDFs using multimodal embeddings and Vector Search.&lt;/P&gt;
&lt;P&gt;Governed deployment, evaluation, and monitoring&lt;BR /&gt;Enforce unified governance (access, lineage, auditing, sharing) across data, models, tools, and agents with Unity Catalog—no bolt‑on silos.&lt;/P&gt;
&lt;P&gt;Measure and improve quality with MLflow Evaluation and Agent Evaluation (LLM-as-a-judge, custom scorers), consistent offline→online assessment, and trace-level root cause analysis.&lt;/P&gt;
&lt;P&gt;Monitor production with AI Gateway-enabled inference tables to log requests/responses and join with usage and model details for observability and retraining loops.&lt;/P&gt;
&lt;P&gt;Build and optimize AI agents, fast&lt;BR /&gt;Use the Mosaic AI Agent Framework to iterate on RAG and tool-calling agents quickly—including evaluation loops, guardrails, and one-click serving from Unity Catalog.&lt;/P&gt;
&lt;P&gt;Prototype in AI Playground, author in code with MLflow ResponsesAgent, and deploy agents** to scalable Model Serving endpoints with credentials scoped by governance.&lt;/P&gt;
&lt;P&gt;Model strategy and customization&lt;BR /&gt;Start with high-quality open models like DBRX (fast MoE, strong on code and reasoning), or query external/managed models through Foundation Model APIs under unified governance.&lt;/P&gt;
&lt;P&gt;Fine-tune and adapt models to your domain with Mosaic AI Training and register/serve them in Unity Catalog to retain full control over weights and IP.&lt;/P&gt;
&lt;/DIV&gt;</description>
      <pubDate>Mon, 01 Dec 2025 19:13:28 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/what-is-the-core-goal-of-your-project-or-what-problem-are-you/m-p/140779#M1472</guid>
      <dc:creator>iyashk-DB</dc:creator>
      <dc:date>2025-12-01T19:13:28Z</dc:date>
    </item>
  </channel>
</rss>

