{"slug": "agentic-data-science-with-the-data-agent-kit", "title": "Agentic data science with the Data Agent Kit", "summary": "Google Cloud released the Data Agent Kit, which connects coding agents to Google Cloud data services through MCP tools and Markdown-based Skills, plus a Visual Studio Code extension for working inside the IDE. The kit is demonstrated building an end-to-end fraud-detection workflow in the Antigravity IDE: loading JSON transaction logs from Google Cloud Storage into a BigQuery table named raw_transactions via Spark Serverless, generating a dbt project for deduplication and enrichment, training a Random Forest classifier on Spark Serverless, and scoring unlabeled transactions, flagging those with an estimated fraud probability of 50% or higher.", "body_md": "Imagine your compliance team notices that payments are taking longer than expected to clear. They suspect fraud, and you’re the data scientist helping figure out which transactions to investigate first. Assembling that shortlist requires ingesting and cleaning raw transaction logs, training a model on past fraud, scoring new records, and scheduling the pipeline to run daily. Here’s how you can build that workflow end to end with an agent, using the Data Agent Kit inside the Antigravity IDE.\n\n[Data Agent Kit](https://cloud.google.com/products/data-agent-kit?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog) helps you work with Google Cloud data through a [plugin for coding agents](https://github.com/GoogleCloudPlatform/data-agent-kit-plugin) or an [extension for Visual Studio Code-based IDEs](https://open-vsx.org/extension/googlecloudtools/datacloud). It brings two significant additions to the workflow:\n\n**Help for your agent:** MCP tools connect your agent to data services. Skills are Markdown files that give it instructions and best practices for working with your data stack\n\n**Tools in your IDE:** work with Google’s [Agentic Data Cloud](https://cloud.google.com/data-cloud?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog), from querying databases to deploying an Airflow pipeline, without leaving your editor\n\nLet’s start with the raw transaction logs in [Google Cloud Storage](https://cloud.google.com/storage?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog). You can ask the agent to create a notebook that loads them into [BigQuery](https://cloud.google.com/bigquery?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog) using [Spark](https://cloud.google.com/products/managed-service-for-apache-spark?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog):\n\nThe agent generates a Jupyter notebook that loads the JSON logs into a BigQuery table named raw_transactions. You can open the notebook, review the code, and run it using a preconfigured Spark Serverless runtime from the IDE.\n\nAfter the notebook runs, you can open the raw_transactions table with the Data Agent Kit. The extension allows you to browse the table and inspect its metadata right from the IDE.\n\nThe records are now in BigQuery, but they aren’t ready for model training yet. First, we’ll handle duplicate and incomplete records, then join the remaining records with info about who sent and received each payment.\n\nLet’s put the cleanup logic into a dbt project so we can run it on each new batch of data. We’ll also test that each transaction appears only once. Prompt the agent:\n\nThe agent generates a dbt project with SQL models for cleaning and enriching the data. Take a look at the generated code to check how it handles duplicates and joins reference tables. Then run dbt build in the terminal. This builds the staging and enriched tables in BigQuery, along with a separate table for records with missing transaction IDs. dbt also runs the uniqueness test.\n\nWe also keep the is_fraud column, which indicates whether a past transaction was fraudulent. We’ll train the model on records with known labels and use it to score new transactions, where we’re unsure yet whether fraud occurred.\n\nWith the data prepared, let’s ask the agent to create a training notebook using a Random Forest classifier running on Spark Serverless.\n\nReview and run the notebook, then check its evaluation output to see how well the model separates fraudulent transactions from legitimate ones. You can also use the Data Agent Kit extension to verify that the trained model artifacts were saved to Google Cloud Storage.\n\nNow we can use the saved model to score transactions that don’t have an is_fraud value yet:\n\nIn this example, the inference notebook scores the unlabeled transactions in BigQuery and sends those with an estimated fraud probability of 50% or higher to the [Spanner](https://cloud.google.com/spanner?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog) review queue. The flagged records help the team decide where to investigate, but they still need to determine whether fraud occurred.\n\nLook at how the inference notebook filters and writes flagged records, then run it. Once it finishes, query the Spanner table in the IDE to inspect the results.\n\nThis table is the list we set out to build. The compliance team can now start reviewing transactions, and we have a workflow that gets records from raw logs into the queue.\n\nSo far, we have been kicking off each step ourselves. We can now connect them so the workflow runs automatically each day.\n\nEach day we will load the latest logs, apply the dbt transformations, and score unlabeled transactions using the saved model. We’ll use the [Managed Service for Apache Airflow](https://cloud.google.com/products/managed-service-for-apache-airflow?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog) to run these steps in order. Ask the agent: \n\nThe agent generates a YAML pipeline definition and deployment configuration. The pipeline definition sets the schedule and dependencies between steps. Meanwhile, the deployment configuration specifies the Airflow environment where it will run.\n\nData Agent Kit then turns the definition into an Airflow DAG, which you can explore as an interactive graph in the IDE. Open the pipeline under “Orchestration Pipelines” and click a task to inspect it. For notebook tasks, you can follow the link straight back to the code.\n\nWith the Airflow environment configured, click “Run pipeline” in the canvas. Data Agent Kit packages the notebooks and dbt project, deploys the DAG, and triggers a run. Open the pipeline’s execution history to follow its progress. You can also select individual tasks to inspect their status, duration, and logs.\n\nAirflow will run the pipeline every day, taking new batches of data from raw logs to the review queue. The compliance team can now focus on flagged transactions, and you’ve automated the work of getting those records to them!\n\nIf you are ready to try this for yourself, we have [designed a codelab](https://codelabs.developers.google.com/dak-data-science-antigravity-ide?hl=en#0) that walks you through the full setup so you can build and run this workflow. You can also [read our documentation](https://docs.cloud.google.com/data-agent-kit/overview?utm_campaign=CDR_0xaea1deef_default_b563520811&utm_medium=external&utm_source=blog) or check out the skills and tools in the open-source repository on [GitHub](https://github.com/GoogleCloudPlatform/data-agent-kit-plugin).", "url": "https://wpnews.pro/news/agentic-data-science-with-the-data-agent-kit", "canonical_source": "https://cloud.google.com/blog/products/data-analytics/bringing-you-the-data-agent-kit/", "published_at": "2026-10-12 16:00:00+00:00", "updated_at": "2026-10-12 16:20:17.057325+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "developer-tools", "ai-tools", "mlops"], "entities": ["Google Cloud", "Data Agent Kit", "Antigravity IDE", "BigQuery", "Google Cloud Storage", "Spark Serverless", "dbt", "Visual Studio Code"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/agentic-data-science-with-the-data-agent-kit", "markdown": "https://wpnews.pro/news/agentic-data-science-with-the-data-agent-kit.md", "text": "https://wpnews.pro/news/agentic-data-science-with-the-data-agent-kit.txt", "jsonld": "https://wpnews.pro/news/agentic-data-science-with-the-data-agent-kit.jsonld"}}