Follow along for how-tos, demos, product news, and more. For company updates, check out @GoogleCloud.
Joined August 2008
- Tweets26.5K
- Following1.6K
- Followers1.3M
- Likes5.7K
Simplify security policy configuration with the new visual match condition builder for Google Cloud Armor.
This tool is useful when configuring rules to protect multi-cloud backends or hybrid deployments. Check out the documentation to learn more → goo.gle/3UaJxyf
Validate your skills in the last course in the Deploy Production Ready Agents learning path—part of the GEAR series.
Earn your advanced skill badge by completing labs that cover ADK, A2A, MCP, and Agent Engine → goo.gle/4jDzP1A
Stop copy-pasting context between chat threads, docs, and Jira.
@MollzMP and Adam Fisher discuss Gemini as one persistent cloud agent ↓
Thank you to everyone who participated in the Cloud Run Hackathon with Product Hunt, and congratulations to our winner, Inferock! 🎉
Learn more about Inferock → goo.gle/48dWw5s
Simplify your commercial model for delivery, scale, and protection with Global Front End Enterprise.
Read the documentation to discover how it unifies Global External Application LB, Cloud CDN, Cloud Armor, and Service extensions into a single package → goo.gle/4jEdUaG
The core formula for scaling agent autonomy via @_lopopolo:
1️⃣ Build small, deterministic PRs
2️⃣ Use agents to operationalize agents to handle PR review
3️⃣ Stack small changes end-to-end over longer arcs
Watch The Agent Factory to learn more → goo.gle/4ePpoVj
Set a goal on a legacy codebase, step away, and come back to verified, production-ready code.
@MollzMP breaks down Gemini 4 Argon ↓
Google Cloud Tech retweeted
Today, we're bringing OpenAI models to Google Cloud's model garden.
We're now the only hyperscale cloud provider offering access to all three leading closed source LLMs—alongside 200+ other models—on a unified enterprise platform → goo.gle/4zJ0VZQ
Big day for the @PyTorch ecosystem at #PyTorchConf2026 🚀
We’re officially open-sourcing TorchTPU—enabling native, hardware-accelerated PyTorch execution across Cloud TPUs and custom infrastructure.
Here’s everything we launched to supercharge your training & inference workloads 🧵👇
goo.gle/4Bl0zdG
2/ Production-grade distributed training on TPUs.
Together with @AIatMeta, we’ve brought TorchTitan on TPU to lifecycle large-scale training recipes natively in @PyTorch.
Scale dense, MoE, and diffusion models across TPU pods with:
⚡ Full-step capture via Graph Trainer & SimpleFSDP
🧩 Pluggable Pallas kernels (Splash Attention, grouped MoE)
🤗 Zero-setup support for 500+ @huggingface models
Check out the optimization playbook and recipes ↓ goo.gle/3WmIdZD
3/ Ready to build?
Whether you're migrating existing PyTorch models or scaling greenfield systems, the TPU Developer Hub has you covered with quickstarts, architecture guides, and code samples.
⭐ Star the repo on @github and start building ↓ goo.gle/4i0sLuH
On this week's livestream, we'll demonstrate how to use Antigravity CLI with custom skills and hooks to perform interactive code reviews, catching vulnerabilities that may slip through vibe-coded or manually written features when the code is written.
xitter.cf/i/broadcasts/1NxaroZbR…
Google’s approach to security review with agents xitter.cf/i/broadcasts/1NxaroZbR…
Ever kick off an 8-hour agent job overnight, only to wake up to find it paused after 10 seconds because of a permission check?
Hear from @SmithaKolan and @lukeschlangen on why asynchronous human-in-the-loop continuity is a game changer for cloud agents → goo.gle/3WfnN4M
Moving autonomous agents off your laptops into production? Here are some practical ways to lock down your agent sandboxes ↓
Send audit logs outside the sandbox in real time.
Stream your telemetry directly from the outside host into Cloud Trace and Cloud Audit Logs as the agent runs.
🔗Read the full article from @tweetpraveen for more tips ↓
dev.to/googleai/7-ways-to-lo…
