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 →

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 🧵👇

Gemini Agent is built for high-ceiling work where EACH task gets its own computer. You can choose Gemini 4 Argon or Claude Opus 5.5. 10 things that make it a universal work Agent (read till the end to see what a REAL work agent looks like): 1. One Agent, one API Chat, autonomous objectives, and code generation from a single interface. Assign it work, schedule it, or have it respond to events. 2. Coworker agents with their own identities It creates job-specific sub-agents, each with its own identity, and computer running in parallel for hours or days. Each Coworker agent gets its own Workspace account: an agent email, calendar, Drive, and presence in your company directory. You mention it in Chat. It acts under its own identity, not yours, and sees only what you share. 3. Everywhere, including headless Web, iOS, Android, Windows, Mac, command line, Workspace, Microsoft 365, Slack. It also runs as a headless agent with no dedicated interface. 4. Work 24/7 in the cloud It keeps one set of memories, context, and personalization graph across every device and channel. Work that takes hours or days keeps running after you close your laptop. You never have to re-brief it. 5. Layers of memory that improve over time - Session: the task in front of it, even when it runs for days. - Semantic: a structured knowledge base it builds as it reads documents, talks to people, and works with other agents. - Procedural: how a job gets done, including skills it writes for itself. - Episodic: everything it has done before. 6. Proactive by design It does not wait to be prompted. An email asking you for a deck gets flagged as delegatable, one click to hand off. Your inbox ranks by what matters, not by what just arrived, and tells you why. 7. Tools and skills, with company registries Salesforce, ServiceNow, Jira, Git, Confluence, Microsoft 365, Slack, BigQuery, Databricks, Postgres, Snowflake, your desktop files, and any MCP server inside or outside your network. Teams publish their own tools and skills to a shared company registry. 8. Model Choice so you are not locked in It runs each job on the model that fits best, running across the Gemini and Claude models from Anthropic today, with other private and open models to come. 9. Governed like an employee Every agent gets a cryptographically attested identity with least-privilege permissions, and an audit trail attributed to the agent rather than a person. Agents run in a sandbox behind Agent Gateway, an AI network firewall. Write the policy once and it applies to every agent. 10. Costs you can actually cap Smart Routing puts each workload on the model with the best performance at the lowest cost. Set a hard spend limit in Cloud Billing and that project's agent pauses until you resume it in one click. Thank you for reading so far. Stay tuned for updates. We are 100% committed to make it the best Agent for work.

Our borderless Lakehouse lets Gemini query AWS and Azure with no variable egress fees, read directly from Salesforce Data 360, SAP, ServiceNow, and Workday without copying data, and federate open Apache Iceberg tables across Databricks Unity, Snowflake Horizon, and AWS Glue →

Smart Storage is a game-changer for dark, unstructured data. Smart Storage enriches files in place and writes metadata directly onto the source object, so Gemini gets instant context and your security ACLs never drift.

Get ready to run, hunt, and hack with the Cloud Run hackathon on Product Hunt! Deploy your side project to production with Cloud Run and launch it on @ProductHunt on October 14 to join Learn more →

We teamed up with @GoogleCloudTech for a Cloud Run Hackathon October 14th! To kick things off, we're celebrating on the leaderboard so you can meet the people behind Cloud Run. They'll be checking out the launches, and hanging out on Product Hunt all week starting today to talk architecture, troubleshoot setups, and cheer you on as you prep for launch day.

On this week's livestream, Arthur Soroken sits down with Amir Sadeghian, PhD and Ali Sadeghian, the brother-duo and co-founders behind Astrocade, to discuss how generative AI and Gemini multimodal models are redefining game development.

Take this course to learn to design hierarchical agent trees and deterministic workflow agents while identifying the ideal hosting environment to ensure your AI agents are secure, scalable, and production-ready →

Building enterprise AI should be powerful, not painful. In this DevEx program sprint, we tested agent governance on Gemini Enterprise from the ground up—using standard external accounts and zero internal shortcuts to find + fix developer friction fast ↓

Leaving performance on the table in latency-critical workloads? With AlphaEvolve, you get an autonomous evolutionary loop that pairs Gemini’s architectural reasoning in the cloud with domain-specific benchmark harnesses on your target infrastructure →

Today we’re introducing Gemini 4 Argon. It delivers frontier performance in complex workflows across real-world software engineering, knowledge work, and cybersecurity defense with an industry-leading 1M token output limit.

Terminal test runs won't catch multi-turn agent regressions. In Ep 3 of Agent Clinic, Dani Zamora & @matt_feroz build an automated eval suite for a LangGraph agent in 60 mins. Here's the 4-step framework to go from vibes to benchmark ANY AI agent →

An unharnessed LLM can express intent, but it has no way to execute actions. The harness is what connects model intent to the real world: reading files, running tests, and executing code. Watch @BillyJacobson’s demo →

The secret to high-performing coding agents isn't just raw reasoning power—it's the 3 connected layers: 🔹 Model 🔹 Harness 🔹 Knowledge Watch "3 Layers of a High-Performing Agent Stack" with @SmithaKolan to learn more →