Building with Claude on Google Cloud

A live build from zero to deployed in thirty minutes. We'll build a feedback app spanning five roles and the full software lifecycle, using Claude and Google Cloud alongside subagents, MCP servers, and custom skills. You can test the finished app at the end of the session.

May 7, 202626mWatch on YouTube ↗

WHAT IT’S REALLY ABOUT

End-to-end app building with Claude Code on Google Cloud

The presenter frames an enterprise software lifecycle with five personas (PM, UI/UX, engineer, security, analyst) and shows how Claude Code can augment each step.
He demonstrates rapid prototyping from a simple hand-drawn wireframe into a usable multi-page UI using Claude Code, including a planning mode for structured implementation.
He outlines and implements a cloud-native backend using Google Cloud services (Cloud Run, Firestore, BigQuery, Looker) assisted by Google Cloud documentation/skills exposed via MCP servers.
He shows parallel development using Claude Code subagents to build the API, ingestion pipeline, and dashboard components concurrently, including automated testing steps.
He runs a security review workflow to catch and fix issues, then deploys the application to Cloud Run and uses Claude to generate a feedback summary from collected responses.

IDEAS WORTH REMEMBERING

5 ideas

ADC makes Claude Code-on-GCP setup frictionless for teams.

Using Application Default Credentials avoids manual API key management and rotation, and the setup wizard helps pick project/region and available Claude models quickly.

Claude on Google Cloud is positioned for enterprise deployment needs.

The talk highlights pay-per-token pricing (no message caps), optional provisioned throughput for production workloads, regional/global endpoints, and keeping data/policies within your GCP project.

“Plan mode” reduces rework by forcing a design/implementation proposal first.

Before generating code, Claude produces a structured plan you can review and modify (including aligning to design docs/Figma-like inputs) to better match standards and expectations.

MCP servers turn “fresh documentation” into executable developer assistance.

By connecting Claude Code to Google’s Developer Knowledge API via an MCP server, Claude can propose architectures and implementation steps without the user already knowing GCP specifics.

Skills complement MCP by solving common building blocks quickly and consistently.

Where MCP helps with architecture and up-to-date guidance, prebuilt “skills” target concrete tasks like deploying an API on Cloud Run or wiring Cloud Run to Firestore.

WORDS WORTH SAVING

5 quotes

So the goal here today is just try to make it better.

— Ivan Nardini

What I'm gonna show you is, uh, how you can use Claude on Google Cloud to build and, uh, deploy application end-to-end.

— Ivan Nardini

So first of all, because you pay for what you use, so the con- the usage of a Claude models on Google Cloud is per token, so you don't receive a message, uh, message cap.

— Ivan Nardini

So what we are saying here is that you don't need to know, uh, like how to deploy an application on Google Cloud. You can just leverage Claude Code and this MCP server that we expose now on, on Google Cloud side to build application like this one.

— Ivan Nardini

I was trying to show you how, like, all the components of, uh, Cloud Code, including skills, MCP server, subagents, they can really, like, speed up the process of software, uh, development.

— Ivan Nardini

Claude Code setup via Application Default Credentials (ADC)Why run Claude models on Google Cloud (billing, throughput, governance)Plan mode for UI/UX implementationMCP servers: Developer Knowledge API, BigQuery, Looker integrationGoogle Cloud Skills for targeted implementation tasksSubagents for parallel component developmentSecurity review: OWASP checks, service accounts/least privilege, automated fixesDeployment to Cloud Run; data flow to Firestore and BigQuery; dashboards in Looker

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.