{"id":26936,"date":"2026-10-26T10:36:53","date_gmt":"2026-10-26T03:36:53","guid":{"rendered":"https:\/\/gcloudvn.com\/?p=26936"},"modified":"2026-10-26T10:36:53","modified_gmt":"2026-10-26T03:36:53","slug":"data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent","status":"publish","type":"post","link":"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/","title":{"rendered":"Data Agent Kit is now GA: Bring Google Data Cloud to any coding agent"},"content":{"rendered":"<p>Today, Google Cloud Data Agent Kit is generally available. Data Agent Kit is a free set of Model Context Protocol (MCP) tools and agent skills that lets the coding agent you already use work directly with your Google Cloud data products, whether you're using Antigravity, Claude Code, Codex, or other popular tools.<\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/dak_blog_banner-max-2500x2500\/\" rel=\"attachment wp-att-26867\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26867\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1.png\" alt=\"\" width=\"2436\" height=\"1200\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1.png 2436w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1-768x378.png 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1-1536x757.png 1536w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1-2048x1009.png 2048w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/dak_blog_banner.max-2500x2500-1-18x9.png 18w\" sizes=\"auto, (max-width: 2436px) 100vw, 2436px\" \/><\/a><\/p>\n<p>With GA, we are adding support for BigQuery Graph, Bigtable, and Managed Service for Apache Spark access to your open Lakehouse, along with dozens of quality-of-life improvements that make everyday work faster and smoother.<\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da\/\" rel=\"attachment wp-att-26866\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26866\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da.gif\" alt=\"\" width=\"1878\" height=\"1190\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da.gif 1878w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da-768x487.gif 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da-1536x973.gif 1536w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/00-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent-da-18x12.gif 18w\" sizes=\"auto, (max-width: 1878px) 100vw, 1878px\" \/><\/a><\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_88 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Data_Agent_Kit_la_gi\" >What is Data Agent Kit?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Cach_thuc_hoat_dong\" >How it works<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Ung_dung_thuc_te\" >What you can build<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Phan_tich_va_Do_thi_BigQuery_va_BigQuery_Graph_Moi_trong_GA\" >Analytics and graph: BigQuery and BigQuery Graph (New in GA)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Co_so_du_lieu_van_hanh_va_thoi_gian_thuc_Spanner_AlloyDB_Cloud_SQL_va_Bigtable_Moi_trong_GA\" >Operational and real-time databases: Spanner, AlloyDB, Cloud SQL, and Bigtable (New in GA)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Lakehouse_va_Spark_Managed_Service_for_Apache_Spark_va_Lakehouse_for_Apache_Iceberg_Moi_trong_GA\" >Lakehouse and Spark: Managed Service for Apache Spark and Lakehouse for Apache Iceberg (New in GA)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Duong_ong_du_lieu_va_dieu_phoi_dbt_Dataform_va_Managed_Service_for_Apache_Airflow\" >Pipelines and orchestration: dbt, Dataform, and Managed Service for Apache Airflow<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Nang_cao_trai_nghiem_lap_trinh_vien\" >Improving the developer experience<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#San_sang_cho_doanh_nghiep\" >Ready for business<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Cai_dat_va_Bat_dau\" >Install and get started<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Lua_chon_1_Cai_dat_Tien_ich_mo_rong_IDE\" >Option 1: Install the IDE Extension<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/gcloudvn.com\/en\/data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent\/#Lua_chon_2_Cai_dat_Plugin_CLI\" >Option 2: Install the CLI Plugin<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h3><span class=\"ez-toc-section\" id=\"Data_Agent_Kit_la_gi\"><\/span><b>What is Data Agent Kit?<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Coding agents have become remarkably good at writing SQL, PySpark, and pipeline code. What they don't have by default is context about your environment: which tables exist, how they're partitioned, which ones your team trusts, or why last night's job failed. Without that, even a strong agent has to work from assumptions, and you end up pasting schemas and error logs into the chat to fill in the gaps.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Data Agent Kit fills that gap with two things:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">MCP tools: Connections to more than 15 Google Data Cloud services, so your agent can inspect schemas, run queries, read job logs, and manage resources in your live environment.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\">Google-authored skills: Open-source instructions from Google Cloud engineers that teach your agent data best practices, like optimizing BigQuery SQL, designing Bigtable row keys, and building dbt (data build tool) pipelines.<\/li>\n<\/ul>\n<p>You can use Data Agent Kit wherever you already work: as an IDE extension for VS Code, Antigravity IDE, Cursor, and other VS Code-compatible editors; as a plugin for Antigravity 2.0, Antigravity CLI, Claude Code, and Codex; or in Cloud Shell and Cloud Workstations, where it comes pre-installed. The IDE extension also brings a lightweight version of the Google Cloud console into your editor, so you can browse data, run queries, and review your agent's work without switching windows.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Cach_thuc_hoat_dong\"><\/span><b>How it works<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Say you ask your agent, \"Forecast next month's demand for our top-selling products and check whether we have enough inventory to meet it.\" Data Agent Kit loads the relevant skills, so the agent follows Google's best practices for the task. It searches <\/span><a href=\"https:\/\/cloud.google.com\/dataplex\/docs\/introduction?utm_campaign=CDR_0xaea1deef_default_b566338695&amp;utm_medium=external&amp;utm_source=blog\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">Knowledge Catalog<\/span><\/a><span style=\"font-weight: 400;\">to find the sales and inventory tables your team trusts. It then uses MCP tools to run a forecast in <\/span><a href=\"https:\/\/cloud.google.com\/bigquery?utm_campaign=CDR_0xaea1deef_default_b566338695&amp;utm_medium=external&amp;utm_source=blog\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">BigQuery<\/span><\/a><span style=\"font-weight: 400;\">, check current stock levels in AlloyDB for PostgreSQL, and bring the combined answer back to your editor or terminal. Every step runs with your own IAM permissions.<\/span><\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/01-data-agent-kit-is-now-ga-bring-google-d-max-2200x2200\/\" rel=\"attachment wp-att-26865\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26865\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1.png\" alt=\"\" width=\"2200\" height=\"988\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1.png 2200w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1-768x345.png 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1-1536x690.png 1536w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1-2048x920.png 2048w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/01-data-agent-kit-is-now-ga-bring-google-d.max-2200x2200-1-18x8.png 18w\" sizes=\"auto, (max-width: 2200px) 100vw, 2200px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">How Data Agent Kit connects to data<\/span><\/p>\n<h3><span class=\"ez-toc-section\" id=\"Ung_dung_thuc_te\"><\/span><b>What you can build<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Data Agent Kit covers analytics, operational databases, the Lakehouse, and pipelines. Here's what that looks like in practice, starting with what's new at GA.<\/span><\/p>\n<h4><span class=\"ez-toc-section\" id=\"Phan_tich_va_Do_thi_BigQuery_va_BigQuery_Graph_Moi_trong_GA\"><\/span><b>Analytics and graph: BigQuery and BigQuery Graph (New in GA)<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<p><span style=\"font-weight: 400;\">Graphs are a natural way to explore relationships, like which products people buy together or how suppliers connect to your inventory. Building one usually means hand-writing CREATE PROPERTY GRAPH DDL, learning GQL, and working out which keys actually form edges.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Instead, you describe the graph you want and your agent builds it. The bigquery-graph-author skill maps your tables to nodes and edges, checks each proposed relationship against the actual data, and shows you a plan to approve before creating anything. It can even start from an ER diagram or data model you already have. The bigquery-graph-query skill then writes the GQL, and the graph visualizer in the IDE lets you click through the results.<\/span><\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/02-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bq\/\" rel=\"attachment wp-att-26864\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26864\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/02-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bq.gif\" alt=\"\" width=\"930\" height=\"555\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/02-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bq.gif 930w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/02-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bq-768x458.gif 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/02-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bq-18x12.gif 18w\" sizes=\"auto, (max-width: 930px) 100vw, 930px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">Building and visualizing a BigQuery property graph.<\/span><\/p>\n<h4><span class=\"ez-toc-section\" id=\"Co_so_du_lieu_van_hanh_va_thoi_gian_thuc_Spanner_AlloyDB_Cloud_SQL_va_Bigtable_Moi_trong_GA\"><\/span><b>Operational and real-time databases: Spanner, AlloyDB, Cloud SQL, and Bigtable (New in GA)<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<p><span style=\"font-weight: 400;\">Some features have to load instantly, like a personalized feed, a live counter, or a \"recently viewed\" rail on your storefront. Bigtable is built for exactly that, and it rewards a well-designed row key.<\/span><\/p>\n<p>With GA, Bigtable joins Spanner, AlloyDB, and Cloud SQL as a fully supported database in Data Agent Kit. The new bigtable-basics skill designs your schema around how the data will be read and flags hotspots and full table scans before you create anything. Your agent can then create the table and query it with GoogleSQL, with column families flattened into readable columns. In the IDE, you can browse Bigtable instances and tables in the catalog explorer and run queries from the SQL editor.<\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/03-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bi\/\" rel=\"attachment wp-att-26863\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26863\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/03-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bi.gif\" alt=\"\" width=\"930\" height=\"553\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/03-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bi.gif 930w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/03-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bi-768x457.gif 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/03-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_bi-18x12.gif 18w\" sizes=\"auto, (max-width: 930px) 100vw, 930px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">Agent-guided Bigtable schema design and querying.<\/span><\/p>\n<h4><span class=\"ez-toc-section\" id=\"Lakehouse_va_Spark_Managed_Service_for_Apache_Spark_va_Lakehouse_for_Apache_Iceberg_Moi_trong_GA\"><\/span><b>Lakehouse and Spark: Managed Service for Apache Spark and Lakehouse for Apache Iceberg (New in GA)<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<p>Your agent could already query the Apache Iceberg tables in your Lakehouse through BigQuery. Now it can also work with those same tables using serverless Spark on Managed Service for Apache Spark, with no cluster to manage. Each session keeps its state, so temporary views carry across statements, and you get Iceberg's full feature set, including branching, time travel, and schema evolution.<\/p>\n<p><span style=\"font-weight: 400;\">Your tables don't all have to live on Google Cloud, either. The federate-lakehouse-catalog skill connects your Lakehouse to AWS Glue and Databricks Unity Catalog, so your agent can query that data in place without building an ingestion pipeline first.<\/span><\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/04-data-agent-kit-is-now-ga-bring-google-d-max-1800x1800\/\" rel=\"attachment wp-att-26862\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26862\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/04-data-agent-kit-is-now-ga-bring-google-d.max-1800x1800-1.png\" alt=\"\" width=\"1716\" height=\"981\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/04-data-agent-kit-is-now-ga-bring-google-d.max-1800x1800-1.png 1716w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/04-data-agent-kit-is-now-ga-bring-google-d.max-1800x1800-1-768x439.png 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/04-data-agent-kit-is-now-ga-bring-google-d.max-1800x1800-1-1536x878.png 1536w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/04-data-agent-kit-is-now-ga-bring-google-d.max-1800x1800-1-18x10.png 18w\" sizes=\"auto, (max-width: 1716px) 100vw, 1716px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">Branching and querying Iceberg tables with Managed Service for Apache Spark.<\/span><\/p>\n<h4><span class=\"ez-toc-section\" id=\"Duong_ong_du_lieu_va_dieu_phoi_dbt_Dataform_va_Managed_Service_for_Apache_Airflow\"><\/span><b>Pipelines and orchestration: dbt, Dataform, and Managed Service for Apache Airflow<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<p>Once your logic works, your agent can turn it into a pipeline that runs on its own. It writes dbt or Dataform models, then the gcp-pipeline-orchestration skill schedules them together with your notebooks as an Orchestration Pipeline on Managed Service for Apache Airflow. Pipelines can also include Gemini Enterprise Agent Platform steps, like uploading a model or running batch inference.<\/p>\n<p><span style=\"font-weight: 400;\">In the IDE, you can follow each run on a visual pipeline canvas. If a task needs attention, click Diagnose to hand its logs to your agent. Troubleshooting skills for Airflow and Spark trace the root cause and propose a fix for you to approve.<\/span><\/p>\n<p><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/05-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_pi\/\" rel=\"attachment wp-att-26861\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26861\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/05-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_pi.gif\" alt=\"\" width=\"1280\" height=\"720\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/05-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_pi.gif 1280w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/05-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_pi-768x432.gif 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/05-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_pi-18x10.gif 18w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">Troubleshooting a failed Airflow DAG with an agent.<\/span><\/p>\n<h3><span class=\"ez-toc-section\" id=\"Nang_cao_trai_nghiem_lap_trinh_vien\"><\/span><b>Improving the developer experience<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">GA also streamlines setup and day-to-day workflows. When you get started, you simply sign in once and select the Google Cloud services you use. Data Agent Kit automatically enables the required APIs, installs the matching skills, and configures your MCP servers with no manual setup files. Inside the IDE, the SQL editor and notebooks now support inline code generation, @ references to tables, and diff views for suggested changes. The extension also shares your active project, open file, and the error from the query you just ran with your agent, so asking it to \"fix this query\" just works.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">We also made the core tools faster and more responsive. New Spark notebooks automatically create and select a Spark Connect runtime, and Spark SQL queries in the editor run in isolated sessions with built-in execution metrics. The catalog explorer now loads faster and includes BigQuery public datasets in the sidebar. Tuned notebook skills help your agent finish notebook tasks more quickly while using fewer tokens.<\/span><\/p>\n<h3><span class=\"ez-toc-section\" id=\"San_sang_cho_doanh_nghiep\"><\/span><b>Ready for business<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Data Agent Kit is included at no additional cost; you pay standard pricing only for the Google Cloud services your agent uses. Skills also steer the agent toward cost-aware query patterns, like checking partition keys and running a dry run before executing a BigQuery query to avoid accidental full-table scans. And because the skills are open source on GitHub, your team can audit them, fork them, or write custom skills for your own internal standards.<\/span><\/p>\n<p>For access control, the agent connects as you or as a service account you impersonate, so row- and column-level security policies apply automatically. Admins can also govern MCP access with Identity and Access Management (IAM), screen MCP traffic with Model Armor, and scope agents with VPC Service Controls and Principal Access Boundary policies.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Cai_dat_va_Bat_dau\"><\/span><b>Install and get started<\/b><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">You can set up Data Agent Kit in under a minute in either your IDE or your terminal.<\/span><\/p>\n<h4><span class=\"ez-toc-section\" id=\"Lua_chon_1_Cai_dat_Tien_ich_mo_rong_IDE\"><\/span><b>Option 1: Install the IDE Extension<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">IDE extension: Search for \"Google Cloud Data Agent Kit\" in the Extensions panel of VS Code, Antigravity IDE, Cursor, or any VS Code-compatible editor. You can also install it from the VS Code Marketplace or Open VSX.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Antigravity 2.0: Go to Settings &gt; Customizations &gt; Build with Google Plugins, then download Data Agent Kit.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Cloud Shell and Cloud Workstations: Already installed by default; just open the editor and sign in.<\/span><\/li>\n<\/ul>\n<h4><span class=\"ez-toc-section\" id=\"Lua_chon_2_Cai_dat_Plugin_CLI\"><\/span><b>Option 2: Install the CLI Plugin<\/b><span class=\"ez-toc-section-end\"><\/span><\/h4>\n<p>Run the command for your preferred coding agent using the official GoogleCloudPlatform\/data-agent-kit-plugin repository:<\/p>\n<p><span style=\"font-weight: 400;\"># Antigravity CLI<\/span><\/p>\n<p><span style=\"font-weight: 400;\">agy plugin install https:\/\/github.com\/GoogleCloudPlatform\/data-agent-kit-plugin<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u200b<\/span><span style=\"font-weight: 400;\"># Claude Code<\/span><\/p>\n<p><span style=\"font-weight: 400;\">claude plugin install data-agent-kit-starter-pack@claude-plugins-official<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u200b<\/span><span style=\"font-weight: 400;\"># Codex CLI<\/span><\/p>\n<p><span style=\"font-weight: 400;\">codex plugin marketplace add GoogleCloudPlatform\/data-agent-kit-plugin<\/span><\/p>\n<p><span style=\"font-weight: 400;\">codex plugin add dak@dak-marketplace<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Then try a first prompt:<\/span><\/p>\n<p><span style=\"font-weight: 400;\">What are this week\u2019s fastest rising search terms in the US that weren\u2019t in the last week\u2019s top 10? Use the BigQuery public Google Trends dataset.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"><a href=\"https:\/\/gcloudvn.com\/en\/introducing-skills-in-the-gemini-app-and-workspace-plus-whats-next-for-gems\/attachment\/06-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_cl\/\" rel=\"attachment wp-att-26860\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-26860\" src=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/06-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_cl.gif\" alt=\"\" width=\"930\" height=\"611\" srcset=\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/06-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_cl.gif 930w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/06-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_cl-768x505.gif 768w, https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/10\/06-data-agent-kit-is-now-ga-bring-google-data-cloud-to-any-coding-agent_cl-18x12.gif 18w\" sizes=\"auto, (max-width: 930px) 100vw, 930px\" \/><\/a>Plugin Data Agent Kit \u0111ang ch\u1ea1y trong Claude Code.<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>Google Cloud Data Agent Kit \u0111\u00e3 ch\u00ednh th\u1ee9c ph\u00e1t h\u00e0nh di\u1ec7n r\u1ed9ng. Data Agent Kit l\u00e0 b\u1ed9 c\u00f4ng c\u1ee5 Model Context Protocol (MCP) v\u00e0 k\u1ef9 n\u0103ng agent mi\u1ec5n ph\u00ed gi\u00fap agent l\u1eadp tr\u00ecnh b\u1ea1n \u0111ang d\u00f9ng l\u00e0m vi\u1ec7c tr\u1ef1c ti\u1ebfp&hellip;<\/p>","protected":false},"author":2,"featured_media":26859,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[1,135],"tags":[],"class_list":["post-26936","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-kienthuc","category-google-cloud-platform","entry","has-media"],"_links":{"self":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/26936","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/comments?post=26936"}],"version-history":[{"count":1,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/26936\/revisions"}],"predecessor-version":[{"id":26937,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/26936\/revisions\/26937"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/media\/26859"}],"wp:attachment":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/media?parent=26936"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/categories?post=26936"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/tags?post=26936"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}