Google Cloud’s cover photo
Google Cloud

Google Cloud

Software Development

Mountain View, California 3,453,980 followers

The new way to cloud.

About us

Google Cloud accelerates every organization’s ability to digitally transform its business and industry. We deliver enterprise-grade solutions that leverage Google’s cutting-edge technology, and tools that help developers build more sustainably. Customers in more than 200 countries and territories turn to Google Cloud as their trusted partner to enable growth and solve their most critical business problems.

Website
https://cloud.google.com/
Industry
Software Development
Company size
10,001+ employees
Headquarters
Mountain View, California

Updates

  • View organization page for Google Cloud

    3,453,980 followers

    If your testing strategy for AI agents consists of running 3 manual prompts in your terminal and saying “looks good to me,” you don’t have an agent ready for production—you have a prototype. The hardest part about autonomous loops (like LangGraph or CrewAI) isn’t hard crashes—it’s silent failure. Agents will execute without throwing a single 500 error while quietly hallucinating or generating subpar outputs. In episode 3 of the AI Agent Clinic, Dani Zamora sits down with Matthew Feroz, Developer Advocate at Merge, to upgrade his DocsHound agent in 60 minutes. At first, you'll see that Matt was confident in his agent’s output. But once we hooked up an automated evaluation pipeline, the data told a different story: a 33% quality score on documentation accuracy—a complete blind spot that manual testing never caught. In this episode, we break down the 4-step framework to evaluate any AI agent: 1️⃣ Map Execution Flow: Pointing coding agents to source code to inspect inner workings. 2️⃣ Standardize Telemetry: Using OpenTelemetry and OpenInference so your eval toolset works across any framework. 3️⃣ Define Quality Rubrics: Turning subjective developer expectations into structured LLM-as-a-judge metrics. 4️⃣ Visualize Direction: Running scorecards to spot exact regressions in latency, token cost, and accuracy. Check out the full 60-minute build → https://goo.gle/4hHEXiO

    • No alternative text description for this image
  • View organization page for Google Cloud

    3,453,980 followers

    Spanner Omni is now generally available! The deploy-anywhere version of Spanner is here—ready to power your most demanding production workloads in your private data centers, in a multi-cloud deployment, or even for testing locally on a laptop. Spanner Omni brings Google-grade consistency, availability, scale, and interoperable multi-model capabilities directly to your next agentic AI applications. Discover how to achieve unparalleled flexibility and power wherever your data lives → https://goo.gle/4dgYsgx

    • No alternative text description for this image
  • View organization page for Google Cloud

    3,453,980 followers

    Today, Timex Group announced the launch of Timex Tales, an interactive storytelling experience using Google Gemini, designed to help parents and teachers guide children in learning how to read a traditional analog clock. ⏰ Through personalized adventures, generated by Nano Banana, children step into stories alongside a cast of playful characters, each guiding them through the moments of a day as time unfolds across imaginative worlds. Timex Tales allows each child to become the hero of their own time-learning adventure and build lasting confidence with analog time-telling, while maintaining a safe, family-focused experience. 🔗 Swipe through to see how it works and try Timex Tales yourself → https://lnkd.in/eyr2rB7u

  • On this week's livestream, learn how to build cross-cloud agents using a borderless Lakehouse architecture. Explore how BigQuery handles multimodal data and native AI functions to generate automated descriptions, update product metadata, and generate embeddings. Discover step-by-step techniques for joining structured and unstructured data, performing vector search, configuring data chunks, and connecting external platforms into your Google Cloud Lakehouse workflow.

    Build cross-cloud agents with the borderless Lakehouse

    Build cross-cloud agents with the borderless Lakehouse

    www.linkedin.com

  • Around 22 billion tokens per minute are currently processed across Google’s APIs and developer products. With 1 token equaling roughly 0.75 words, that is the equivalent of processing the entire English Wikipedia more than three and a half times over every single minute. Scaling infrastructure to sustain that velocity requires rethinking systems from first principles—co-designing hardware and software, optimizing network fabrics, and maximizing goodput across TPUs, GPUs, and CPUs to eliminate idle capacity. For enterprise leaders scaling their own AI workloads, these architectural lessons provide a practical roadmap. Watch this Six Five Summit conversation between Mark Lohmeyer and The Futurum Group’s Daniel Newman breaking down the new infrastructure paradigm → https://goo.gle/4d73bBv

Affiliated pages

Similar pages