skills.rest
google
googleOFFICIAL
Explore all skills by this author →
Website𝕏@GoogleOSSGitHub

google-cloud-solution-agentic-ai-borderless-data-lakehouse

Designs a governed borderless open data lakehouse architecture on Google Cloud with agentic AI integration.

19.1k|1.5k|Updated Mar 31, 2026
Search Tags:#architecture design#terraform#Google Cloud#multicloud#data lakehouse#Apache Iceberg#Agentic AI
One-click install
npx skills add https://github.com/google/skills --skill google-cloud-solution-agentic-ai-borderless-data-lakehouse
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google-cloud-solution-agentic-ai-borderless-data-lakehouse
Source: https://github.com/google/skills/tree/main/skills/cloud/google-cloud-solution-agentic-ai-borderless-data-lakehouse
Command: npx skills add https://github.com/google/skills --skill google-cloud-solution-agentic-ai-borderless-data-lakehouse

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Designing a secure, governed data lakehouse that joins data across Google Cloud, other cloud providers, and on-premises sources for AI agents is complex and error-prone. This Skill guides an agent through a structured four-phase workflow to discover requirements, design the architecture, generate Terraform-based implementation plans, and validate the deployment.

Core Features & Use Cases

  • Requirements Discovery: Structured questioning to capture data sources, metadata federation, security, and analytics requirements, producing a confirmed technical decomposition.
  • Solution Design: Maps components to Google Cloud products (Lakehouse for Apache Iceberg, Managed Service for Apache Spark, BigQuery, Cross-Cloud Interconnect) with Mermaid architecture diagrams and design recommendations across security, reliability, cost, performance, and sustainability pillars.
  • Implementation & Validation: Generates Terraform IaC, step-by-step deployment instructions, and verification scripts (gcloud, curl) with a compiled validation report.
  • Use Case: An enterprise wants AI agents to query data spread across AWS S3, on-premises databases, and Google Cloud. The Skill produces a complete solution architecture guide, deployment automation, and validation plan for a federated lakehouse.

Quick Start

Ask the agent to design a borderless open data lakehouse architecture that connects your existing data sources across clouds to AI agents on Google Cloud.

Frequently Asked Questions about google-cloud-solution-agentic-ai-borderless-data-lakehouse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a multicloud data lakehouse on Google Cloud?▼

Follow the four-phase workflow: discover requirements, map components to Google Cloud products like Lakehouse for Apache Iceberg and Managed Service for Apache Spark, generate Terraform IaC and deployment instructions, then validate the deployment with verification scripts.

How to connect AI agents to data across multiple clouds?▼

Use a borderless lakehouse architecture where a central catalog unifies fragmented data sources, and a serving subsystem with BigQuery data agents lets users query the consolidated data. Cross-Cloud Interconnect provides private connectivity to other cloud providers.

BigQuery vs Managed Service for Apache Spark for data processing?▼

Managed Service for Apache Spark with Lightning Engine is recommended for complex programmatic transformations and vectorized borderless joins. BigQuery is an alternative that queries data in place on external clouds using standard SQL, reducing data movement but offering less flexibility for custom code.

Does this approach work with on-premises data sources?▼

Yes, the workflow explicitly identifies hybrid and on-premises components during requirements discovery and supports federated queries across Google Cloud and external sources including on-premises systems, using Dedicated or Partner Interconnect for connectivity.

When should I not use a borderless lakehouse architecture?▼

Avoid this approach for simple single-cloud data warehouses or non-AI workloads. It is designed for multi-product architectures that join data across clouds and serve AI agents, so simpler needs are better served by a standard BigQuery warehouse.

Related Skills

Explore More Software Engineering Skills→
ACGSpgpACGSpgp

hybrid-cloud-networking

Configure VPNs and dedicated connections between on-premises networks and AWS, Azure, or GCP.

Official
Advanced
gemini-cli-extensionsgemini-cli-extensions
161

federate-lakehouse-catalog

Federate Google Cloud Lakehouse catalogs to remote Iceberg catalogs.

Official
Advanced
coreymaypraycoreymaypray
1

cloud-security-architect

Audit AWS, Azure, and GCP cloud security posture against CIS benchmarks.

Community
Advanced
MCDxAIMCDxAI
8

minecraft-fabric-dev

Coordinate documentation sync, version listing, decompilation, mapping selection, and mixin validation for Minecraft Fabric mod development.

Official
Advanced