20 stories
The model can write the code. It can't open your files, run your tests, or ask before doing something risky. The software that does all of that is the AI harness, and this crash course shows you how to design one.
We spent over 1,000 hours hands-on testing Google's new frontier model: Gemini 4 Argon. With an industry-leading 1-million-token output limit and deep long horizon reasoning, Argon doesn’t just take in massive context—it delivers massive, verified solutions without losing the plot.
Looker onboarding skill → https://g.dev/ai/looker-developer-onboarding Are you logging into Looker for the first time or looking to streamline your LookML modeling workflows?
Watch the full keynote here → https://g.dev/ai/gemini-at-work-keynote Luke Schlangen and Smitha Kolan break down the updates from Gemini at Work 2026: * One Persistent Cloud Agent: Shared memory for chat, code, background jobs, and Gemini Omni across web, mobile, desktop, CLI, browser, Workspace,…
Most voice-controlled browser agents feel broken because every click or page load blocks the voice stream. In this episode, we build a live voice agent that controls a real browser, clicking, typing, and navigating, without killing the conversation.
Genkit → https://g.dev/ai/build-agentic-apps Flutter → https://g.dev/flutter/build-for-any-screen Go → https://g.dev/cloud/build-with-go In this episode of The Agent Factory, Luke Schlangen sits down with Abdallah Shaban, Outbound Product Manager for Frameworks and Languages at Google Cloud.
Learn more about Harness → https://g.dev/ai/harness Get started with Harness on the Google Cloud Marketplace today → https://g.dev/cloud/marketplace Learn more about Google Gemini → https://g.dev/ai/learn-more-gemini Meeting developers directly where they work eliminates context switching and…
[Codelab] Author LookML with Agentic Coding Tools → https://g.dev/ai/looker-agentic-lookml Learn about the 5 core tools in the Agentic Looker Developer Stack: Looker Skills, Looker CLI, Looker Managed MCP server, MCP-toolbox-for-databases, and the Looker VSCode Extension.
How can coding agents the exact context they need to build a project without repeating yourself on every single prompt? In this video, Annie Wang and Tilde Thurium break down the markdown-based specification files that define how your AI agents should think, design, and execute tasks across your…
AI agents are most powerful when grounded in real organizational data. In this demo, discover how to use Elastic Agent Builder to create an incident-investigation agent powered by Elastic Observability data (logs, metrics, and traces) to quickly diagnose application performance regressions.
Code for this episode → https://g.dev/cloud/repositories Gemini Live API docs → https://g.dev/cloud/gemini-live CDP Page commands → https://g.dev/cloud/devtools-protocol How does an AI voice agent control a real browser while keeping the conversation going?
Join Chrissie for the month of October as she takes over the Google Cloud Tech channel. Be sure to like and subscribe so you don't missing any exciting data analysis tips, tricks, and more! Speaker: Chrissie Goodirch
Learn more about measures here. → https://g.dev/ai/bq-measure In this BigQuery tutorial, you’ll learn how to define graph measures with MEASURE, query them with AGG, and reuse calculations across different groupings.
Is the future of gaming personalized? In this episode, Arthur Soroken (Co-founder of Google AI Futures Fund) sits down with Amir and Ali, the brother-duo and co-founders behind Astrocade.
Stop prompting one-by-one. 🛑 When Google Developer Experts built an AI race coach at Sonoma Raceway, they didn't rely on single prompts. They orchestrated a synchronized ADK agent swarm on a Pixel 10: one agent ingesting 10Hz telemetry at the edge, while Gemma 4 fired zero-latency audio coaching…
Manual prompt tweaking isn't a testing strategy. Here is how to actually evaluate AI agents for production. For more information, check out the Agent Clinic episode linked below the title. Speakers: Dani Zamora, Matthew Feroz Products Mentioned: Antigravity, Gemini, Google Cloud, Vertex AI
Manual code tweaking isn't a testing strategy. Here is how to actually evaluate AI agents for production. For more information, check out the Agent Clinic episode linked below the title.
In this video, Anupam Phoghat sits down with Martin Omander to walk through a practical build of an agentic cloud application that actually makes business decisions.
Showing 18 of 20 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
