[
  {
    "id": "databricks-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Create and deploy an ETL (extract, transform, and load) pipeline for data orchestration using Lakeflow pipelines and Auto Loader.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-2",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "The Databricks CLI (command-line interface) allows you to interact with the Databricks platform from your local terminal or automation scripts.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "Genie Code is the AI coding and data assistant for developers and technical practitioners in the Databricks workspace.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Host a custom MCP server as a Databricks app to expose your own tools.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Write and run SQL queries with integrated AI assistance, code comments, and version history.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Get automatic insights and recommendations when queries run inefficiently.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/uc-semantics/metric-views",
    "excerpt": "you define the metric once, for example _sum of revenue divided by distinct customer count_, and users can group by any available field.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/genie/",
    "excerpt": "Ask data questions in natural language and get answers grounded in your organization's data.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Create interactive AI/BI dashboards with AI-assisted authoring to share insights across your organization.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/partners/prep/dbt",
    "excerpt": "This page explains what dbt is, how to install dbt Core, and how to connect.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-11",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "To migrate from Databricks CLI version 0.18 or below to Databricks CLI version 0.205 or above, see Databricks CLI migration.",
    "fetchedAt": "2026-09-06T23:57:14.495Z"
  },
  {
    "id": "databricks-docs-12",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/",
    "excerpt": "Databricks notebooks provide real-time coauthoring in multiple languages, automatic versioning, and built-in data visualizations",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-13",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/structured-streaming/concepts",
    "excerpt": "Incrementally and efficiently process new data files as they arrive in cloud storage.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-14",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/partners/prep/dbt",
    "excerpt": "dbt Core enables you to write dbt code in the IDE of your choice on your local development machine and then run dbt from the command line.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-15",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "It generates and runs code, builds pipelines and AI/BI dashboards, debugs errors, and works directly with Unity Catalog tables, columns, and lineage",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-16",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/uc-semantics/metric-views",
    "excerpt": "you define the metric once, for example sum of revenue divided by distinct customer count, and users can group by any available field",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-17",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/delta-sharing/",
    "excerpt": "OpenSharing is the secure data sharing platform in Databricks that lets you share data and AI assets with users outside your organization, regardless of whether they use Databricks.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-18",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/marketplace/",
    "excerpt": "The Open Marketplace, which does not require access to a Databricks workspace.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-19",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/",
    "excerpt": "enforcing access control when you query a table or call a model, tracking lineage as data and AI assets are used, logging activity for auditing",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-20",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/ingestion/",
    "excerpt": "Use it to choose a standard connector by data source and level of pipeline customization.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-21",
    "tier": "claimed-docs",
    "url": "https://www.databricks.com/product/pricing",
    "excerpt": "Databricks offers you a pay-as-you-go approach with no up-front costs. Only pay for the products you use at per second granularity.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-22",
    "tier": "claimed-docs",
    "url": "https://www.databricks.com",
    "excerpt": "From natural language dashboard creation to deep conversational analytics with Genie, this is BI built on AI from the start.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-23",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Use a Databricks notebook to query sample data stored in Unity Catalog and then visualize the query results in the notebook.",
    "fetchedAt": "2026-09-06T23:59:30.686Z"
  },
  {
    "id": "databricks-docs-24",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Train a deep learning model on Databricks and track training runs, hyperparameters, and metrics with MLflow 3.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-25",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Use the AI Playground to query large language models (LLMs) and compare results side-by-side, prototype a tool-calling agent, and export your agent to code.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-26",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Monitor query results, evaluate conditions, and deliver notifications automatically.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-27",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/genie/",
    "excerpt": "Access Genie One from iOS and Android devices to ask data questions, view dashboards, and run Databricks Apps.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-28",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/genie/",
    "excerpt": "Chat with Genie Code, get inline suggestions, and run agentic tasks in your workspace.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-29",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "Run Genie Code as an autonomous agent that plans, runs code, fixes errors, and asks for approval before it uses tools.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-30",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "It generates and runs code, builds pipelines and AI/BI dashboards, debugs errors, and works directly with Unity Catalog tables, columns, and lineage to accelerate multi-step data work.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-31",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Give your agent governed access to third-party and SaaS tools such as Slack, GitHub, Google Drive, Google Calendar, and Gmail",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-32",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "It runs directly on your data lake, supports ANSI SQL with Delta Lake extensions, and provides the tools to build highly performant, cost-effective data warehouses without moving your data.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-33",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/uc-semantics/metric-views",
    "excerpt": "Query metric views from Power BI, Tableau, Sigma, and other external BI tools.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-34",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/marketplace/",
    "excerpt": "Listings include datasets, AI models, notebooks, apps, and Model Context Protocol (MCP) servers.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-35",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/partners/prep/dbt",
    "excerpt": "dbt (data build tool) is a development environment for transforming data by writing select statements.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-36",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/structured-streaming/concepts",
    "excerpt": "Process data for real-time workloads with end-to-end latency as low as five milliseconds.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-37",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/",
    "excerpt": "Databricks notebooks provide real-time coauthoring in multiple languages, automatic versioning, and built-in data visualizations for developing code and presenting results.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-38",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/",
    "excerpt": "Unity Catalog operates beneath every data and AI interaction in your workspaces automatically: enforcing access control when you query a table or call a model, tracking lineage as data and AI assets are used, logging activity for auditing, and more.",
    "fetchedAt": "2026-09-07T00:01:00.082Z"
  },
  {
    "id": "databricks-docs-39",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Start your journey with Databricks by signing up for a free trial account.",
    "fetchedAt": "2026-09-07T00:21:48.871Z"
  },
  {
    "id": "databricks-docs-40",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Develop and deploy your first ETL (extract, transform, and load) pipeline for data orchestration with Apache Spark\u2122.",
    "fetchedAt": "2026-09-07T00:21:48.871Z"
  },
  {
    "id": "databricks-docs-41",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "This tutorial also illustrates the use of MLflow to track the model development process, and Hyperopt to automate hyperparameter tuning.",
    "fetchedAt": "2026-09-07T00:21:48.871Z"
  },
  {
    "id": "databricks-docs-42",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Define business metrics with consistent calculations using a semantic layer. Reuse metrics across queries and dashboards.",
    "fetchedAt": "2026-09-07T00:21:48.871Z"
  },
  {
    "id": "databricks-docs-43",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Create AI agent tools using Unity Catalog functions, including third-party integrations and code interpreter tools.",
    "fetchedAt": "2026-09-07T00:21:48.871Z"
  },
  {
    "id": "databricks-docs-44",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/genie/",
    "excerpt": "Discover and interact with shared assets across all workspaces in your account from a single entry point.",
    "fetchedAt": "2026-09-07T00:23:27.272Z"
  },
  {
    "id": "databricks-docs-45",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Wire up Claude, Cursor, MCP Inspector, and other external clients to MCP servers hosted on Databricks.",
    "fetchedAt": "2026-09-07T00:23:27.272Z"
  },
  {
    "id": "databricks-docs-46",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Create a table and grant privileges in Databricks using the Unity Catalog data governance model.",
    "fetchedAt": "2026-09-07T00:23:27.272Z"
  },
  {
    "id": "databricks-docs-47",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/databricks-connect/",
    "excerpt": "Databricks Connect enables developers to develop and debug their code on Databricks compute using any IDE's native running and debugging functionality.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-48",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "allows you to interact with the Databricks platform from your local terminal or automation scripts",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-49",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/sdk-python",
    "excerpt": "you learn how to automate Databricks operations and accelerate development with the Databricks SDK for Python",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-50",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Discover, authenticate to, and call managed, MCP Service, and custom MCP servers from your agent code, then deploy the agent on Databricks Apps.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-51",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/structured-streaming/concepts",
    "excerpt": "Structured Streaming lets you express computation on streaming data in the same way you express a batch computation on static data.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-52",
    "tier": "claimed-docs",
    "url": "https://www.databricks.com",
    "excerpt": "Lakebase is serverless Postgres for applications that scale",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-53",
    "tier": "claimed-docs",
    "url": "https://www.databricks.com",
    "excerpt": "Build high-quality, production-ready AI agents grounded in your data.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-54",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/delta/history",
    "excerpt": "Use history information to audit operations, roll back a table, or query a table at a specific point in time using time travel.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-55",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/marketplace/",
    "excerpt": "publish offerings that Databricks customers can discover, evaluate, and connect with directly from their workspace",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-56",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/",
    "excerpt": "You work with the objects Unity Catalog governs through Catalog Explorer, SQL, the Databricks CLI, and REST APIs.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-57",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/",
    "excerpt": "Navigate the Genie One interface designed for business users. View dashboards, ask natural language data questions, and discover assets shared with you.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-58",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/admin/account-settings/budgets",
    "excerpt": "You can set up budgets to either track account-wide spending, or apply filters to track the spending of specific teams, projects, or workspaces.",
    "fetchedAt": "2026-09-07T01:09:51.934Z"
  },
  {
    "id": "databricks-docs-59",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "Genie Code is the AI coding and data assistant for developers and technical practitioners in the Databricks workspace. It generates and runs code, builds pipelines and AI/BI dashboards, debugs errors",
    "fetchedAt": "2026-09-07T01:11:43.602Z"
  },
  {
    "id": "databricks-docs-60",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/",
    "excerpt": "Inspect the execution plan for a query to identify bottlenecks and optimization opportunities.",
    "fetchedAt": "2026-09-07T01:11:43.602Z"
  },
  {
    "id": "databricks-docs-61",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/admin/account-settings/budgets",
    "excerpt": "Budgets enable you to monitor usage across your account. You can set up budgets to either track account-wide spending, or apply filters to track the spending of specific teams, projects, or workspaces.",
    "fetchedAt": "2026-09-07T01:11:43.602Z"
  },
  {
    "id": "databricks-supp-compliance",
    "tier": "claimed-docs",
    "url": "https://www.databricks.com/trust/compliance",
    "excerpt": "Databricks Trust Center compliance page (\"Ensuring Security, Privacy, & Compliance\") documents attestations including a SOC 2 Type II report available to customers, alongside the platform's certification portfolio.",
    "fetchedAt": "2026-09-07T01:42:38.000Z"
  },
  {
    "id": "databricks-docs-62",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "Genie Code is the AI coding and data assistant for developers and technical practitioners in the Databricks workspace. It generates and runs code, builds pipelines and AI/BI dashboards, debugs errors, and works directly with Unity Catalog tables, columns, and lineage",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-63",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/notebooks/databricks-assistant-faq",
    "excerpt": "Start work directly from Genie Code rather than from an asset like a notebook, run multiple chats in parallel, and persona",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-64",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/dev-tools/databricks-connect/",
    "excerpt": "Just like a JDBC driver, the Databricks Connect library can be embedded in any application to interact with Databricks.",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-65",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/api/workspace/introduction",
    "excerpt": "This reference contains information about the Databricks workspace-level application programming interfaces (APIs).",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-66",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/free-edition",
    "excerpt": "Free Edition gives you an easy-to-use Databricks workspace where you can explore datasets, build and share projects, and work with AI and machine learning tools.",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-67",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/free-edition",
    "excerpt": "Collaborate on data science and ML projects: Use shared notebooks to work with others in real time and publish results for others to review.",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-68",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/structured-streaming/concepts",
    "excerpt": "Use Delta Lake tables as streaming sources and sinks with exactly-once processing guarantees.",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-69",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/marketplace/",
    "excerpt": "Listings include datasets, AI models, notebooks, apps, and Model Context Protocol (MCP) servers. This gives customers a single catalog for finding data, software, and AI capabilities across the Databricks partner ecosystem.",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-70",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/",
    "excerpt": "Unity Catalog operates beneath every data and AI interaction in your workspaces automatically: enforcing access control when you query a table or call a model, tracking lineage as data and AI assets are used, logging activity for auditing",
    "fetchedAt": "2026-09-10T18:22:22.807Z"
  },
  {
    "id": "databricks-docs-71",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "Give your agent governed access to third-party and SaaS tools such as Slack, GitHub, Google Drive, Google Calendar, and Gmail \u2014 through built-in system.ai MCP Services, external MCP servers you register",
    "fetchedAt": "2026-09-10T18:27:39.276Z"
  },
  {
    "id": "databricks-docs-72",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/uc-semantics/metric-views",
    "excerpt": "you define the metric once, for example sum of revenue divided by distinct customer count, and users can group by any available field. The query engine generates the correct computation.",
    "fetchedAt": "2026-09-10T18:27:39.276Z"
  },
  {
    "id": "databricks-docs-73",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/free-edition",
    "excerpt": "Databricks Free Edition is a no-cost version of Databricks designed for students, educators, hobbyists, and anyone interested in learning or experimenting with data and AI.",
    "fetchedAt": "2026-09-10T18:27:39.276Z"
  },
  {
    "id": "databricks-docs-74",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/getting-started/free-edition",
    "excerpt": "Free Edition replaced the legacy Databricks Community Edition, which was retired in 2025. If you previously used Community Edition, sign up for Free Edition to continue your work.",
    "fetchedAt": "2026-09-10T18:27:39.276Z"
  },
  {
    "id": "databricks-docs-75",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/",
    "excerpt": "Data and AI assets such as tables, views, volumes, functions, models, and services (model services and MCP services) follow a three-level namespace (catalog.schema.object).",
    "fetchedAt": "2026-09-10T18:27:39.276Z"
  },
  {
    "id": "databricks-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "I used to be a big fan of the platform because in 2020/2021 it was the only reasonable choice vs AWS/Azure/Snowflake. Today it suffers from feature creep and too many pivots & acquisitions. They are insanely bad at naming features.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-2",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "Coming from hadoop, databricks is utopia. It's stable, fast, scales really well if you have massive datasets. The biggest gripe I have is how crazy expensive it is.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-3",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "Databricks is the Jira of dealing with data. No one wants to use it, it sucks, there are too many features to try to appease all possible users but none of them particularly good.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-4",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "They push Serverless so hard but there are SO MANY limitations and surprise gotchas. It's driving me absolutely insane.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-5",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "No persist() so can't cache dataframes; no good way to get usage info programmatically; can't set Spark config easily (had to hack S3A credentials via options()); Unity Catalog only lets you mount external volumes matching your workspace's cloud provider, blocking cross-cloud setups.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-6",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "They had an excellent Spark-as-a-Service product, at a time when you'd have better luck finding a leprechaun than a reliable self-hosted Spark instance in an enterprise environment.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-7",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/43982777",
    "excerpt": "Databricks' setup of spark saves an incredible amount of time on configuration and infra wiring. It's expensive and opinionated, but default configs give you much better performance out of the box than DIY, without fiddling with partitions.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-8",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=43982777",
    "excerpt": "Maybe unrelated but Databricks is the most annoying garbage I have ever had to use. It fascinates me how anyone uses it by choice.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-9",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/29232346",
    "excerpt": "Snowflake has much more advanced data security - table, column, row level security, dynamic data masking, and zero-copy cloning. Databricks security seems lacking - just table level, only in SQL and Spark, none in R. I liked the Databricks UI and integrated visualizations though.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-10",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=34875353",
    "excerpt": "Not only is Databricks a deplorable company when it comes to HR, but their product is terrible. I really don't get what it's all about. Much rather spin up my own python notebook with my own underlying data storage.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-11",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=29505512",
    "excerpt": "My experience with 'Scala at scale' was extremely unsatisfactory and I found Databricks to give very unhelpful responses to basic performance problems arising from the intersection of Scala and Spark, bordering on gaslighting.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-12",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=36127230",
    "excerpt": "We've been moving our workflows out of Databricks to PostgreSQL to save a ton.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-comm-13",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=36127230",
    "excerpt": "Databricks coined the 'Delta lake' concept and are still (just about) leading the way, but Fabric has the potential to take away marketshare. Databricks need to improve their 'serverless SQL' offering, and add a serious 'data warehouse' component alongside the lake.",
    "fetchedAt": "2026-09-07T00:25:45.793Z"
  },
  {
    "id": "databricks-probe-1",
    "tier": "probe",
    "url": "https://docs.databricks.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.databricks.com/llms.txt # Databricks Documentation\n> Comprehensive documentation for the Databricks Data Intelligence Platform, including guides",
    "fetchedAt": "2026-09-07T00:27:35.593Z"
  },
  {
    "id": "databricks-probe-2",
    "tier": "probe",
    "url": "https://docs.databricks.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://docs.databricks.com/openapi.json, https://docs.databricks.com/swagger.json, https://docs.databricks.com/api/openapi.json, https://docs.databricks.com/.well-known/openapi.json)",
    "fetchedAt": "2026-09-07T00:27:35.593Z"
  },
  {
    "id": "databricks-probe-3",
    "tier": "probe",
    "url": "https://docs.databricks.com/aws/en/agents/mcp-tools",
    "excerpt": "official MCP server documented at https://docs.databricks.com/aws/en/agents/mcp-tools",
    "fetchedAt": "2026-09-07T00:27:35.593Z"
  },
  {
    "id": "databricks-probe-4",
    "tier": "probe",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "official CLI documented at https://docs.databricks.com/aws/en/dev-tools/cli/",
    "fetchedAt": "2026-09-07T00:27:35.593Z"
  },
  {
    "id": "databricks-probe-rt-1",
    "tier": "probe",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "PROBE runtime (recorded 2026-09-06): the Databricks CLI installed via the vendor's brew tap and printed `Databricks CLI v1.15.0` keylessly; its help surface spans workspace, compute, Lakeflow jobs/pipelines, and a raw `databricks api` REST wrapper.",
    "fetchedAt": "2026-09-07T00:33:24.000Z"
  },
  {
    "id": "databricks-probe-rt-2",
    "tier": "probe",
    "url": "https://docs.databricks.com/aws/en/dev-tools/cli/",
    "excerpt": "PROBE runtime (recorded 2026-09-06): the Databricks CLI SHIPS vendor agent skills \u2014 `databricks aitools install --path /tmp/pa-dbx-skills` keylessly wrote 29 plain SKILL.md skill folders (databricks-docs, databricks-dbsql, databricks-lakeflow-connect, databricks-vector-search, \u2026) with agentskills-style frontmatter, installable for Claude Code, Codex, Cursor, Copilot, and more.",
    "fetchedAt": "2026-09-07T00:33:24.000Z"
  },
  {
    "id": "databricks-supp-api-versioning",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/sql/dbsql-api-latest",
    "excerpt": "Docs, \"Update to the latest Databricks SQL API version\": \"The legacy API is deprecated and support will end soon. Use this page to migrate your applications and integrations to the new API version\" \u2014 e.g. \"The API path is now api/2.0/sql/queries, replacing the legacy path of /api/2.0/preview/sql/queries\".",
    "fetchedAt": "2026-09-10T18:30:34.000Z"
  },
  {
    "id": "databricks-supp-versioned-apis",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/aws/en/reference/api",
    "excerpt": "API reference hub lists versioned REST APIs side by side, e.g. \"Jobs v2.0 API \u2014 REST API reference for version 2.0 version of the Jobs REST API. Databricks recommends that you use the latest Databricks REST API for new and existing clients and scripts.\"",
    "fetchedAt": "2026-09-10T18:30:34.000Z"
  },
  {
    "id": "databricks-supp-api-reference-examples",
    "tier": "claimed-docs",
    "url": "https://docs.databricks.com/api/workspace/introduction",
    "excerpt": "API reference (docs.databricks.com/api): \"This reference describes the types, paths, and any request payload or query parameters, for each supported Databricks REST API operation. Many reference pages also provide request and response payload examples. Some reference pages also provide examples for calling a Databricks REST API operation by using the Databricks CLI, the Databricks Terraform provider, or one or more of the Databricks SDKs.\" (No live try-it runner is documented.)",
    "fetchedAt": "2026-09-10T18:32:49.000Z"
  }
]