Evolving Spec-Driven Development: Conductor Now Supports Antigravity
Conductor has evolved from a Gemini CLI extension into a portable plugin, bringing conversational Spec-Driven Development (SDD) to ecosystems like Antigravity CLI and Claude. Rather than relying on strict command sequences, developers can n
Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search
Google Cloud has partnered with Parallel Web Systems to natively integrate Parallel's search infrastructure as a web grounding provider on the Gemini Enterprise Agent Platform. This integration enables developers to anchor their AI agents i
Building scalable AI agents with modular prompt transpilation
To resolve the scaling bottlenecks and runtime errors caused by monolithic system prompts, engineering teams should treat prompts as build artifacts by modularizing instructions into reusable templates. By running these modular "skill files
Systems Engineering Playbook: Optimizing Qwen 3.5-397B MoE on Ironwood (TPU7x)
To serve the 397B-parameter Qwen 3.5 Mixture-of-Experts (MoE) model on Ironwood TPUs, engineers developed a modular JAX/Pallas optimization stack that achieved up to a 4.7x inference speedup for prefill-heavy workloads. The team bypassed se
LiteRT.js, Google's high performance Web AI Inference
We're excited to introduce LiteRT.js, the newest member of the LiteRT family! LiteRT.js is our powerful solution for running machine learning models directly in the browser, extending Google's cross-platform edge AI runtime to the web. Buil
Bridging the Domain Gap: AI Race Coach built with Antigravity and Gemini
On May 23, 2026, fresh off the stage at Google I/O, our Google Developer Experts (GDEs) converged on...
We terminated a TPU mid-training and it recovered in seconds: Introduction to elastic training with MaxText
Distributed AI training is notoriously fragile because losing a single machine typically crashes the entire multi-node job, forcing a time-consuming, full-workload infrastructure restart. To address this, Google’s JAX ecosystem utilizes ela
Build agentic full-stack apps with Genkit
The open-source Genkit framework has introduced the Agents API, a full-stack tool designed to simplify the complex plumbing of conversational AI by packaging message history, tool loops, and streaming into a single interface. The API suppor
Why we built ADK 2.0
Answering the questions of "why we built ADK 2.0". This explains the rationale, some of the features, and why a developer should consider upgrading. This will be published the day after ADK go 2.0 launches.
ML Development in VS Code with Google Cloud Power: Workbench Extension Now Available
The Google Cloud Workbench Notebooks extension for VS Code has officially launched, allowing developers to connect their local IDE to scalable, cloud-based Jupyter environments. This integration streamlines the machine learning lifecycle by
Driving the Agent Quality Flywheel from Your Coding Agent
Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production. To bridge this gap, Google has introduced a new developer skill for coding agents that
Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration
The Agent Development Kit (ADK) for Go 2.0 has been released, introducing a first-class, graph-based workflow engine to help developers compose complex, multi-agent applications. This update adds built-in primitives for human-in-the-loop (H
Measuring What Matters with Jules
AI coding agents are rapidly shifting from reactive assistants that complete tasks when prompted to ...
Build Cross-Language Multi-Agent Team with Google’s Agent Development Kit and A2A
How a Python agent and a Go agent collaborate on contract compliance using the Agent2Agent protocolY...
How A2A is Building a World of Collaborative Agents
Celebrating the first anniversary of the Agent-to-Agent (A2A) protocol, this blog post highlights how the framework enables autonomous AI agents to securely collaborate and hand off tasks without the rigidity of traditional APIs. By delegat
A2UI + MCP Apps: Combining the best of declarative and custom agentic UIs
This post introduces three architectural patterns designed to integrate Model Context Protocol (MCP) Apps and Agent-to-User Interface (A2UI) to solve the tradeoff between highly custom iframe environments and native, declarative rendering.
Announcing the Agentic Resource Discovery specification
An open specification for finding and verifying tools, skills, and agents across the web.Agents are ...
Unlocking the Power of the TPU Stack: Introducing our new Developer Hub
Google has officially launched the TPU Developer Hub, a centralized educational resource designed to help model builders and developers maximize the performance of Google Cloud TPUs. The hub offers code-first resources, open-source recipes,
Enhance Security and Trust: New Session Metadata in Sign in with Google
Google is enhancing Sign in with Google by introducing new OIDC standard claims—specifically auth_time and amr (Authentication Methods Reference) to provide developers with deeper session metadata. These updates allow verified apps to verif
DiffusionGemma: The Developer Guide
DiffusionGemma is an experimental text-generation model built on the Gemma 4 architecture that uses diffusion-based parallel generation instead of token-by-token autoregression, enabling much faster inference, bidirectional context awarenes
Repository-level GitHub Copilot usage metrics generally available
The Copilot usage metrics REST API now reports repository-level activity. Two new endpoints return a daily, per-repository breakdown of pull request activity for Copilot coding agent and Copilot code review.… The post Repository-level GitHu
GitHub Copilot app now available in the usage metrics API
The Copilot usage metrics API now reports the GitHub Copilot app usage in the enterprise and organization 1-day and 28-day reports. This gives enterprise and organization admins visibility into the… The post GitHub Copilot app now available
In-House LLM Serving at Netflix
Cloudflare WAF protects WordPress applications from two high-severity vulnerabilities
Cloudflare has deployed two WAF rules in response to high-severity vulnerabilities disclosed to us by the WordPress security team. The new rules protect all Cloudflare customers using affected WordPress versions, but customers should still
Copilot code review: Customization and configurability improvements
Copilot code review now utilizes a firewall, custom setup steps, and independent runner configurations. It now reads custom instructions from the head branch to allow for easy testing and validation… The post Copilot code review: Customizat
GitHub Mobile: Fix pull request comments with Copilot cloud agent
You can now select Fix with Copilot directly from Copilot code review pull request comments in GitHub Mobile. The button is available both on the pull request’s main view and… The post GitHub Mobile: Fix pull request comments with Copilot c
The cost of saying yes has changed
The cost of writing code dropped; the cost of owning it didn't. A framework for deciding which changes are actually cheap in the AI era. The post The cost of saying yes has changed appeared first on The GitHub Blog.
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
NVIDIA Vera Rubin Maximizes Intelligence per Dollar for Post-Training Workloads — a Key Metric for Agentic AI
Lowest cost per token from extreme codesign maximizes intelligence per dollar for post-training in the agentic era.
Kotlin Turns 15: Celebrate the Kotlin Effect
🎉 Kotlin turns 15! 🎉 For 15 years, you’ve helped shape Kotlin into the language it is today. Whether you’ve built apps, contributed to the ecosystem, taught others, or simply chosen Kotlin for your next project – thank you for being part
A scorecard for the AI age
Sarah Friar, CFO of OpenAI, introduces a practical AI scorecard to measure ROI through useful work, cost per successful task, dependability, and return on compute.
The risk of weather data sabotage is rising
Every morning, airline dispatchers, grid operators, and farmers around the world make decisions based on the same thing: a weather forecast. While these forecasts are something that most people glance at for two seconds, weather predictions
Data downloaded by Vercel Sandbox is now free
no longer bills for data it downloads from the internet. Installing packages, cloning a Git repository, or pulling artifacts and datasets from an external source does not count toward Sandbox Data Transfer usage.Vercel Sandbox Traffic recei
Runtime logs now show cache reasons
Runtime logs now show a Cache Reason explaining why a request wasn't a fresh cache hit, for example a time-based or tag-based revalidation. Use cache reasons to debug misses and improve your hit rate. Cache reasons appear for any response t
GLM 5.2 is 35% off via Novita on AI Gateway
is 35% off on AI Gateway through July 24 when routed through Novita.GLM 5.2 To get the discounted rate, set the model to in the and route requests through Novita:zai/glm-5.2AI SDK After July 24, the model stays available at standard provide
Optimized CDN caching and deploying of immutable static assets
Vercel now reuses static files across deployments for frameworks that output content-addressed assets. It's zero-config: Vercel uses to manage these immutable files alongside your code changes, handling the hard parts like hash collisions,
Vercel Plugin now available in Kimi Code CLI
The is now available in the .Vercel PluginKimi Code CLI Kimi Code can now draw on Vercel platform knowledge on demand, with skills for Next.js, AI SDK, Vercel Functions, and more. The Vercel Plugin also helps Kimi Code stay up to date with
Chat SDK adds native Slack agent support
Chat SDK's now supports the agent messaging experience . Agents built with Chat SDK could already talk in channels and DMs and stream replies token-by-token. This update adds the Agent badge, agent conversations in the Messages tab, suggest
Advanced search for Projects is generally available
The filter bar in GitHub Projects views now supports advanced search, so you can build the exact view you need with logical AND and OR instead of maintaining a separate… The post Advanced search for Projects is generally available appeared
Repository admins can archive pull requests
Repository admins can now archive pull requests to remove them from public view without permanently deleting them. When a pull request is archived, it is closed and locked. Pull requests… The post Repository admins can archive pull requests
REST API endpoints for Visual Studio Subscription management
GitHub Enterprise Cloud admins can now use the following REST API endpoints to programmatically manage Visual Studio Subscription (VSS) assignments: GET /enterprises/{enterprise}/visual-studio-subscriptions: Returns all VSS assignments for
Xcode 27 runner image now in public preview
You can now build and test your Apple applications against Xcode 27 on GitHub-hosted macOS runners. This is now available in public preview. With early access to the latest Xcode… The post Xcode 27 runner image now in public preview appeare
Why teens deserve access to safe AI
Learn how OpenAI is making ChatGPT safer for teens with age-appropriate protections, learning tools, parental controls, and expert partnerships.
Connect more of your apps to Search
You’ll be able to securely link and interact with your go-to services directly in AI Mode.
Create, edit and star in videos with two Google Vids updates
Gemini Omni and personal avatars in Google Vids make video creation easier than ever.
Sharpen the Sword, Skip the Downloads — ‘Onimusha: Way of the Sword’ Is Coming to GeForce NOW
Onimusha: Way of the Sword is coming to GeForce NOW at launch, with the playable demo available this week. It’s joined by Denshattack! rolling in with five new games arriving in the cloud. Plus, GeForce NOW officially launches in India, mov
Newer Models, Same Advantage
Our approach to bioresilience
Google DeepMind and Isomorphic Labs are sharing our joint approach to bioresilience and AI models.
Unified Logs is now in open beta
One searchable view for logs across every Supabase service, with live tail, filtering, and a timeline.
How Cars24 scales conversations and builds faster with OpenAI
Cars24 uses OpenAI-powered voice and chat agents to handle 1M+ monthly conversation minutes, recover 12% of lost leads, and bring agentic workflows to teams across the company.
Security incident disclosure — July 2026
Astro 7.1
Astro 7.1 is about more control: CSP, pagination, dev server, and content collections.
Announcing Rust 1.97.1
The Rust team has published a new point release of Rust, 1.97.1. Rust is a programming language that is empowering everyone to build reliable and efficient software. If you have a previous version of Rust installed via rustup, getting Rust
Write utilization now available in ISR Observability
The now shows subscribers a write utilization metric, helping identify routes that regenerate often but receive few requests. Write utilization is the ratio of cached requests to ISR writes. For routes with low write utilization, consider i
Kimi K3 is now available on AI Gateway
is now available on AI Gateway.Kimi K3 from Moonshot AI K3 is an open-source model with a 1M-token context window and native visual understanding, accepting text, image, and video inputs. Built for long-horizon software engineering, knowled
NVIDIA Introduces New Jetson Thor Computers to Advance Mainstream Robotics and Edge AI
General-purpose robots and autonomous machines are moving from research labs to real-world mass-market deployment, creating demand for compact, power-efficient AI supercomputers capable of running foundation models at the edge. To meet that
Improvements to secret scanning and public monitoring
This week, we’re rolling out several improvements to secret scanning and public monitoring: Resend is now a GitHub secret scanning partner. Secret scanning now detects new secret types from APIclub… The post Improvements to secret scanning
What building Shippy taught us about building agents
GitHub for Beginners: Your roadmap to mastering the GitHub essentials
New to GitHub? This beginner's guide explains version control, repositories, and pull requests—plus everything else you need to start working confidently on GitHub. The post GitHub for Beginners: Your roadmap to mastering the GitHub essenti
Model Routing Is Simple. Until It Isn’t.
Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest version of its flagship LLM, GPT-5.6. OpenA
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Hierarchical Interest Representation is a research area for Meta Ads. We’re exploring an upstream representation layer over the universe of Ads entities – users, advertisers, products, services – learning unified embeddings that connect use
The US is advancing AI safety through state and federal action
OpenAI outlines a “reverse federalism” approach to AI governance, where state laws help build a national framework for safe, democratic AI.
CISA and Partners Publish Guidance to Help Software Manufacturers and Online Service Providers Work With Security Researchers
NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry
Home to leading manufacturers, robotics pioneers, infrastructure builders and iconic gaming companies, of course, Japan is one of the world’s centers of AI — building across the full stack with NVIDIA technologies. This week NVIDIA and its
GPT-Red: Unlocking Self-Improvement for Robustness
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
How Speechify serves 500,000 dynamic pages to 60 million users on Vercel
Speechify on Vercel 500,000+ pages served across 40+ languages Cut costs 50% by auto-scaling with Fluid compute Zero user impact on bad deploys with Instant Rollbacks started as a tool for people with dyslexia. Cliff Weitzman, Founder & CEO
GitHub Copilot in Visual Studio — June update
June 2026 is about visibility and trust with a clearer view of your GitHub Copilot usage, a new trust layer for MCP servers, and the first C++ scenarios for the… The post GitHub Copilot in Visual Studio — June update appeared first on The G
Welcome Inkling by Thinking Machines
Introducing Real World VoiceEQ: Measuring the human quality of voice AI
Vercel Connect support in GitHub Tools
now has first-class support for through the new subpath. Instead of storing a long-lived personal access token, your agent mints short-lived, scoped GitHub tokens at runtime from a connector. There is no secret to store, rotate, or leak.Git
Faster, predictable project linking in the Vercel CLI
The now resolves your team before discovering projects, then searches for projects only in that team instead of sweeping every team you belong to. Linking is faster and more predictable, and every command that establishes a link (, , , , an
Inkling from Thinking Machines is now available on AI Gateway
is now available on AI Gateway.Inkling from Thinking Machines Inkling is a broad generalist model, trained across agentic, reasoning, coding, instruction-following, factuality, vision, and audio tasks rather than optimized for a single doma
Vercel Workflows trace viewer now has a minimap
The trace viewer for now has a minimap that shows the entire run in one view.Vercel Workflows Drag the viewport to pan, resize it to zoom, or drag across the minimap to select a new section. Click anywhere on the minimap to jump to that poi
Chat SDK adds Discord Components V2 support
You can now send Discord bot messages with , an opt-in layout system that treats text, images, files, and buttons as flexible components you can arrange in any order.Components V2 Set the adapter's option to and cards render with native con
Nemotron Labs: How Open Models Give Enterprises and Nations AI They Can Trust, Control and Customize
Enterprises have plenty of powerful models to choose from. The real test is whether the AI an enterprise builds uniquely addresses the needs of the business: improving workflows, tapping into domain knowledge and exceeding standards for acc
Celebrating 25 years of visual search innovation
Google Images is turning 25. Here’s a look back at some major milestones — and new ways to explore and create visual content.
Why Performance per Watt Is the Ultimate Metric for AI Infrastructure Efficiency
Power is AI infrastructure’s inescapable constraint. How many tokens an AI factory can generate within a fixed power budget determines its revenue and profitability. Because of this, performance per watt — a metric that can’t be gamed, only
A broken DNSSEC rollover took down .al. Now 1.1.1.1 tells you when validation is bypassed
When a failed DNSSEC key rollover took down the .al TLD, we deployed a Negative Trust Anchor to restore resolution. This time, though, clients didn't have to take our word for it: 1.1.1.1 returned EDE 33, a new DNS error code that signals d