Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Orchestrate Workflows with the Data Agent Kit

Google via Google Skills

Go to class Write review

Coursera

AI, Data Science & Cloud Certificates from Google, IBM & Meta

Scrimba

Free courses from frontend to fullstack and AI

Overview

Google, IBM & Meta Certificates – 40% Off

One plan covers every Professional Certificate on Coursera.

Unlock All Certificates

This course brings AI-driven, natural-language data engineering into the IDE and CLI workflows you already use. Built on the Agent Development Kit (ADK), the Data Agent Kit connects to a wide array of Google Cloud services, including BigQuery, Spanner, BigLake, Dataproc, and Managed Airflow. By using it, you can collapse days of pipeline scaffolding, data build tool (dbt) authoring, and orchestration wiring into prompt-driven sessions. As an intermediate-to-advanced practitioner, you will learn to build a data agent with the Agent Development Kit (ADK). You'll wire up the Model Context Protocol (MCP) layer, and use your agent to explore catalogs, transform data, train models, and orchestrate scheduled pipelines on Google Cloud.

Syllabus

Module: Foundations of agentic data engineering

Foundations of agentic data engineering
Scenario setup with Cymbal Superstore
The Cymbal discount initiative
Data engineering agent interfaces
The Data Agent Kit Architecture
ADK patterns
Module summary
Knowledge check

Module: Build and install your environment

Build and install your environment
Build a basic ADK data agent
Install the Data Agent Kit starter pack
Configure the Data Agent Kit VS Code extension
Module summary
Knowledge check

Module: Authentication and MCP connectivity

Authentication and MCP connectivity
Service account impersonation
Local and remote MCP servers
Connect to BigQuery, Spanner and Cloud SQL
Module summary
Knowledge check

Module: Discover Cymbal Superstore data

Discover Cymbal Superstore data
Browse the catalog
Universal search
Chat-driven schema, lineage and quality inspection
Module summary
Knowledge check

Module: Generate transformations for the discount pipeline

Generate transformations for the discount pipeline
Organize data using the medallion architecture
Generate SQL transformations
BigQuery DataFrames and notebooks
Module summary
Knowledge check

Module: Orchestrate pipelines

Orchestrate pipelines
Build DAGs with natural language
Schedule and GitHub Actions deployment
Monitoring through the agent
Module summary
Knowledge check

Module: Resolve pipeline incidents

Resolve pipeline incidents
Tracing lineage to resolve reconciliation gaps
Diagnosing pipeline failures
Module summary
Knowledge check

Module: Model discount elasticity with BigQuery ML

Model discount elasticity with BigQuery ML
Train the discount elasticity model
Inference and drift monitoring
Module summary
Knowledge check

Module: Secure agent environments

Secure agent environments
Apply least privilege with the MCP Tool User role
Principal access boundary
IAM deny policies for MCP
Module summary
Knowledge check

Module: Guard against prompt injection

Guard against prompt injection
Document guardrails
Configure Model Armor
The prompt injection threat model
Module summary
Knowledge check

Course quiz

Quiz

Your Next Steps

Completion

Tags

united states

Reviews

Start your review of Orchestrate Workflows with the Data Agent Kit