DEV Community: Jen Harvey

Claude Haiku 5.5 is available on Google Cloud

Jen Harvey — Wed, 07 Oct 2026 18:06:52 +0000

Hey developers!

If you’ve been building autonomous agents or multi-agent orchestrations, you already know the pain: latency degrades the user experience, and high token volume stretches production budgets.

Developer choice is important to us so today, we're excited to share that Anthropic’s Claude Haiku 5.5 is officially available on Google Cloud!

As the fastest, most efficient member of the Claude 5.5 family, Claude Haiku 5.5 is engineered from the ground up for high-volume, latency-sensitive agentic work. It is designed to be the ultimate supporting player in your agent systems.

Is it time for you to try it? -> https://console.cloud.google.com/agent-platform/publishers/anthropic/model-garden/claude-haiku-5-5

And enjoy this Haiku about Claude Haiku 5.5:

Fast subagent flies,
Model Garden hosts the spark,
Agents run in light.

Claude Sonnet 5.5 is now available on Google Cloud

Jen Harvey — Mon, 28 Sep 2026 18:53:36 +0000

Designed for coding and knowledge work, it helps you build features, and create clean work materials quicker with a lower cost-per-task at faster speed.

👉 Try it today: [https://console.cloud.google.com/agent-platform/publishers/anthropic/model-garden/claude-sonnet-5-5]

Claude on Google Cloud workshop | NYC | 9/30

Jen Harvey — Fri, 25 Sep 2026 11:50:46 +0000

On Wednesday, September 30, Anthropic and Google Cloud are co-hosting a hands-on developer workshop in New York City. It runs from 8:30am to 12:30pm at the Google office, and is designed for engineers and technical leaders who want to get past evaluating AI coding tools and into actually using them.

The morning covers Claude Code and Claude Desktop on Google Cloud. Most of the time is spent in a hands-on lab session, and participants leave with a working setup. Anthropic and Google Cloud engineers will be on-site throughout to answer technical questions.

During the session, you will have the opportunity to:

See how Claude fits into your existing workflows across the software development lifecycle
Learn best practices around integrating Claude into your Google Cloud environment
Understand how to build on your existing security and compliance requirements
Work through guided labs with Anthropic and Google Cloud experts available throughout
Walk away with a working setup

RSVP today

Claude Opus 5.5 is now available on Google Cloud

Jen Harvey — Tue, 22 Sep 2026 17:48:24 +0000

Everyday complex tasks? No problem. Opus 5.5 handles long-running coding and knowledge work while keeping you in the loop along the way, all at a lower price per token. Get started in Model Garden today!

Claude Fable 5.1 is now available on Agent Platform!

Jen Harvey — Tue, 01 Sep 2026 18:28:57 +0000

Claude Fable 5.1 is officially available in the Model Garden on Agent Platform.

Built for long-running, high-stakes work, Fable 5.1 puts frontier intelligence into production across your code, documents, and research.

👉 Try it today and let us know what you're building: Claude Fable 5.1

Tech webinar: How to control costs & measure ROI for Claude Code on GCP - 9/1 12pm PT.

Jen Harvey — Mon, 24 Aug 2026 17:33:07 +0000

If your team is running or planning to deploy Claude Code on Google Cloud, managing spend and measuring business impact is essential.

Roy Arsan (Anthropic) and Ivan Nardini (Google Cloud) are hosting a deep-dive webinar on September 1, 2026 @ 12:00 PM PT on setting up governance via the Claude apps gateway on GCP.

What you'll learn:

Measuring ROI: Map Claude Code usage to productivity metrics like commits, PRs, and cost per commit.
Tracking adoption: Monitor active developers, session counts, and skill/plugin usage across teams.
Controlling costs: Set centralized model access rules and spend caps by user, team, or org.
Ensuring accuracy: Capture infrastructure-level telemetry so reports mirror real developer activity.

anthropic.com

Claude Opus 5 is Live on Agent Platform 🚀

Jen Harvey — Fri, 24 Jul 2026 17:37:35 +0000

Claude 5 Opus is officially available in the Model Garden on Agent Platform!

Built for highly complex, long-running agentic workflows, Claude 5 Opus brings advanced capabilities in coding, vision, and deep reasoning - allowing businesses to deploy next-generation AI agents with minimal oversight.

Using Claude 5 Opus on Agent Platform keeps your data inside your private Google Cloud network, controls access with IAM, and ensures your data is never used for model training. Built with high-security enterprise environments in mind, it is alsoZero Data Retention (ZDR) compatible.

Find it in the Agent Platform Model Garden 🌱

🚀 Securing Agentic Coding: Announcing the Claude Apps Gateway for Google Cloud

Jen Harvey — Thu, 02 Jul 2026 02:53:02 +0000

As agentic coding tools like Claude Code scale across engineering teams, platform and security architects face a critical challenge: How do you govern local AI clients without slowing down developers?

Google Cloud has announced the Claude apps gateway for Google Cloud to solve exactly this.

Instead of managing scattered API keys on local laptops, the gateway is a stateless container that you deploy directly inside your own private Google Cloud environment. It serves as a secure proxy, routing developer traffic safely to Agent Platform.

Diving straight into the code? No problem! Find the full walkthrough here.

Claude Sonnet 5.0 now available on Google Cloud

Jen Harvey — Tue, 30 Jun 2026 18:59:28 +0000

If you're building autonomous agents, your toolkit just got an upgrade - Claude Sonnet 5.0 is now natively available on Google Cloud!

You can now access Sonnet 5.0, alongside Claude Opus 4.8, directly through the Gemini Enterprise Agent Platform.

The best part about running Claude on Google Cloud? Your data stays yours. By deploying directly on the Agent Platform, you bring Anthropic's reasoning right to where your enterprise data already lives - backed by Google's secure-by-default infrastructure. Bring the model to your data, not the other way around.

Try it now!

Did you want more Claude on Cloud? ☁️ Let's talk about Securing Agents at Scale

Jen Harvey — Wed, 24 Jun 2026 15:25:19 +0000

Did you want more Claude on Cloud? Well, look no further. We have something for you happening today (6/24) at 10:00 AM PT.

Building autonomous agents that can take actions across systems and make decisions without manual human review is incredibly powerful—but it also creates a real challenge for security and IT teams. How do you enforce what an agent is allowed to do? How do you trace and audit its actions?

Join us today for a deep-dive technical session with Roy Arsan (Applied AI @ Anthropic) and Ivan Nardini (Developer Relations Engineer @ Google Cloud) where we'll solve exactly that. We'll be building Claude agents in production using the Claude Agent SDK and showing you how to secure and monitor them at scale.

🛠️ What we're covering:

Identity & Access Management: Giving each agent a scoped identity and enforcing per-agent and per-user policies using Agent Identity, Cloud IAM, and Agent Gateway.
Runtime Protection: Using Model Armor to detect and block prompt injection, tool poisoning, and data leakage on the fly.
Observability: Emitting OpenTelemetry traces and audit events into Google Cloud Observability via the Anthropic Agent SDK, and using permission layers to enforce policy on every tool call.

If you're building agentic workflows with LLMs on Google Cloud, you won't want to miss this one.

👉 Register and join us live!

See you at 10 AM PT! 🚀

Claude Fable 5 is Now Generally Available on Google Cloud! 🚀

Jen Harvey — Tue, 09 Jun 2026 18:44:05 +0000

Good news for Claude devs deploying on Google Cloud. Claude Fable 5, Anthropic’s latest frontier model, is now generally available on Google Cloud. This launch is the latest proof point of our ongoing commitment to bring the industry's latest models straight to our Agent Platform.

Claude Fable 5 brings the best of Anthropic model capabilities to all customers, with strong safeguards designed to make it safe for general use. Designed for complex, multi-step reasoning, Claude Fable 5 is good for demanding tasks like advanced software development, long-horizon agents, and deep multimodal document analysis. For more information about this release, visit Anthropic’s blog.

Build with Claude Fable 5 and other models from Anthropic — including Claude Opus 4.8 and Claude Sonnet 4.6 — today on Agent Platform.

Scaling Intelligence Workshop: Google NYC, Thursday, May 28th 🚀

Jen Harvey — Tue, 19 May 2026 23:37:00 +0000

Do I just post about cool events? Maybe? But that's good, right? Now here's another!

Scaling Intelligence: Accelerating HPC and Inference Workflows.

If you’re building or scaling Generative AI infrastructure, you already know the stakes. Balancing the massive compute demands of LLMs with strict production latency and data security requirements is a massive architectural hurdle.

Whether you're tackling real-time streaming analytics, automated compliance pipelines, or complex risk modeling, your underlying infrastructure shouldn't be your bottleneck.

On Thursday, May 28th, we’re hosting an exclusive, hands-on workshop at Google NYC (111 8th Ave) designed specifically for engineers, architects, and tech leaders: Scaling Intelligence: Accelerating HPC and Inference Workflows.

🛠️ The Tech Breakdown
This isn't a high-level pitch; we're diving into the actual plumbing required for breakthrough performance:

Next-Gen Compute Architectures: Blueprinting high-throughput infrastructure built to handle concurrent, low-latency inference workloads at scale.
The Hardware & Software Stack: Get a closer look at optimizing workloads using Google Cloud’s new G4 VMs (powered by the massive NVIDIA RTX Pro 6000 Blackwell architecture) alongside TensorRT for maximum throughput.
Hands-on Labs: Bring your laptop. You'll get practical experience deploying and optimizing state-of-the-art open-source models like Gemma and Llama 3, with live guidance from Google Cloud and NVIDIA AI experts.

👥 Bring the Whole Squad
Infrastructure decisions don't happen in a vacuum. To get the most out of the hands-on labs and architecture deep-dives, we highly encourage bringing a cross-functional team (2–4 people) across:

AI/ML Architecture & Engineering
Platform Engineering / DevSecOps
IT & Infrastructure Leadership

Aligning your data scientists with your infrastructure engineers is the fastest way to unblock your production roadmap.

📍** Logistics & Details**
Where: Google NYC (111 8th Ave)

When: Thursday, May 28 | 12:00 PM – 4:00 PM (Stick around for the networking reception right after!)

Note on Availability: Spaces are strictly limited to ensure high-quality, hands-on coaching and meaningful architectural reviews during the labs.

👉 Register your team here to secure your spot