by Daryl Ducharme, Google Open Source & Alan Blount, Cloud AI

At Google, we know that building on open source gives teams the freedom and flexibility to use meaningful technologies faster. Openness drives innovation and security, and it is core to our mission. As we look toward the future of computing, we want to ensure that developers across all open source communities have the foundational tools they need to build secure and collaborative AI systems.

That is why we are excited for you to get to know the "A2Family"—a suite of open source protocols and tools designed to help you build, connect, and scale your AI agents.

A2A: The cornerstone of agent interoperability

The Agent2Agent (A2A) Protocol is an open standard designed to enable seamless communication and collaboration between AI agents. It provides the definitive common language for agent interoperability in a world where agents are built using diverse frameworks and by different vendors.

Originally developed by Google, A2A has now been donated to the Linux Foundation. As a famous open source aphorism reminds us: "If you want to go fast, go alone. If you want to go far, go together." A2A brings this collaborative philosophy to AI, allowing agents to delegate sub-tasks, exchange information, and coordinate actions to solve complex problems that a single agent cannot.

MCP & Skills: Agents need tools and skills

Since day one A2A has loved MCP, and we love skills too ♥️. Agents discover, negotiate, converse, make plans, adapt when those plans don't work out – that's a different interaction pattern than a tool and that's what A2A was built for. But for your agents to function, they need access to tools, and instructions on how to use those tools safely and securely. While MCP and A2A might not be from the same origin story, they are a family that works better together.

When you're not sure – if it's a quick deterministic resource or action, it's a tool, but if you may end up with a conversation, it's an agent. Another good mental model is "are you the expert agent which uses tools" (MCP) or "is there some other expert agent you are collaborating with" (A2A).

A2UI: A protocol for agent-driven interfaces

When agents need to communicate with humans, how can they safely send rich interfaces across trust boundaries? Instead of relying on text-only responses or risky code execution, we use A2UI.

A2UI enables AI agents to generate rich, interactive user interfaces that render across web, mobile, and desktop platforms—without executing arbitrary code. It is secure by design, allowing agents to use only pre-approved components from your catalog through declarative component descriptions.

You may also have heard of MCP Apps (formerly MCP UI). It is a complementary alternative to A2UI which ships your agent driven widget inside of an iframe orchestrated with MCP events and tool calls. There are some interesting ways of configuring A2UI and MCP Apps together, for generative UI inside of an iframe or generative UI driving the iframe.

The AG UI protocol, developed by CopilotKit, is a standard for connecting agents to front ends with low latency. It makes developer lives much easier, with integrations to most agent frameworks and front ends. If you are using AG UI, you already have both A2UI and A2A support!

AP2: Securing the agent economy

When an autonomous agent initiates a payment, current systems struggle with questions of authorization, authenticity, and accountability. To solve this, we introduced the Agent Payments Protocol (AP2), an open protocol for the emerging Agent Economy.

Available as an open extension for the A2A protocol, AP2 is designed to enable secure, reliable, and interoperable agent commerce for developers, merchants, and the payments industry. The protocol engineers trust into the system using verifiable digital credentials (VDCs), which are tamper-evident, cryptographically signed digital objects that serve as the building blocks of a transaction.

UCP: The common language for agentic commerce

While AP2 secures the transaction, the Universal Commerce Protocol (UCP) defines the building blocks for the entire shopping journey, from discovering and buying to post-purchase experiences. UCP provides a common language for platforms, agents, and businesses, allowing the diverse commerce ecosystem to interoperate through a single standard without the need for custom builds.

UCP seamlessly connects different systems using open industry standards, featuring built-in support for both the A2A and AP2 protocols. It empowers retailers to meet customers wherever they are, ensuring that businesses retain control of their own rules and remain the Merchant of Record with full ownership of the customer relationship.

Bringing it all together with ADK

Protocols need a solid foundation to run on. Enter the Agent Development Kit (ADK).

Technically not part of the A2Family, ADK is an open-source agent development framework that lets you build, debug, and deploy reliable AI agents at enterprise scale. Available in Python, TypeScript, Go, and Java, ADK helps you build production agents, not just prototypes. It connects everything together, allowing you to easily equip your agents with tools, integrate them with the A2A protocol, and scale them globally on your infrastructure of choice.

Google champions collaboration, transparency, and shared progress to build a better future for everyone through open technologies. We are thrilled to share these tools with you and cannot wait to see what we can build together.

What kind of multi-agent workflows are you planning to build with the A2Family? Let us know in the comments below or tag us on social media!

The Stable channel has been updated to 148.0.7778.56/.57 for Windows and Mac as part of our early stable release to a small percentage of users. A full list of changes in this build is available in the log.

The Beta channel has been updated to 148.0.7778.56 for Windows, Mac and Linux.

A partial list of changes is available in the Git log. Interested in switching release channels? Find out how. If you find a new issue, please let us know by filing a bug. The community help forum is also a great place to reach out for help or learn about common issues.

Chrome Release Team
Google Chrome

To provide a more streamlined and reliable experience, we have unified our forecasting infrastructure. Google Ads API v24 introduces an updated GenerateKeywordForecastMetrics method that simplifies the planning process by focusing on the metrics that most directly impact your performance.

What's changing?

To streamline our systems and focus on the primary data that drives successful Search planning, Google Ads API v24 introduces the following refinements:

1. Alignment with Bidding Strategies

To provide a more consistent experience across Google Ads tools, forecasts now focus exclusively on the primary metrics that your chosen bidding strategy directly impacts. This alignment ensures that the data you use for planning is synchronized with the high-impact performance indicators for your actual campaigns:

• Manual CPC and Maximize Clicks: Forecasts provide clicks, average CPC, and cost.
• Maximize Conversions: Forecasts provide conversions, average CPA, and cost.
• Metric Focus: To maintain consistency across the platform, forecasts no longer include cross-metric data (such as conversion estimates for click-oriented strategies) or secondary metrics like impressions and conversion value.

2. Streamlined Request Parameters

We have made the following updates to simplify forecasting requests, improve system reliability, and remove inputs which have a minimal effect on overall forecast accuracy:

• CampaignToForecast.geo_modifiers[] is replaced by CampaignToForecast.geo_target_constants[]
• ForecastAdGroup.biddable_keywords[] is replaced by ForecastAdGroup.keywords[].
• The following fields are removed:
  • CampaignToForecast.keyword_plan_network
  • CampaignToForecast.negative_keywords
  • ForecastAdGroup.max_cpc_bid_micros
  • ForecastAdGroup.negative_keywords
  • CriterionBidModifier

Timeline

The transition follows our standard release and sunset cycle:

• April 2026: Google Ads API v24 is available with the updated GenerateKeywordForecastMetrics functionality.
• February 2027: Google Ads API v23 is scheduled for sunset. At this time, all versions of the Google Ads API will utilize this unified forecasting infrastructure.

Next Steps

Developers that use GenerateKeywordForecastMetrics should review their integrations to ensure compatibility with the updated parameter set in v24. Review the Generate Forecast Metrics guide and the GenerateKeywordForecastMetrics v24 reference for the latest usage details.

If you have any questions about this announcement or want to discuss it with our team and the community, please reach out to us on our Ads and Measurement Community Discord server.

 - Laura Chevalier, Google Ads API Team

GFiber offers flexible installation options including setting things up yourself or with a professional technician, and ensures your connection is strong from day one by administering a signature battery of tests to validate internet performance to, from and inside your home. No matter how you choose to get started, your GFiber installation—whether you choose a professional tech or a self-installation kit—is always $0. We don't believe in 'activation fees' or charging you just to pick up your equipment.

We offer a seamless self-installation kit for quick and easy setups, and we also provide a premium professional installation with dedicated, on-time appointments that are available as soon as the same or next day. On install day, we’ll text you when your tech is on their way, or you can track the tech yourself on the GFiber App. Over 95% of the time, our pros arrive within the 30 minute arrival window of your appointment time, and you can track their location and ETA in real-time via the Tech Tracker in the GFiber App. During your appointment, our pro will thoroughly test your setup on-site, and we’ll run remote diagnostics to double-check that everything is performing at its best.

What to expect during your GFiber installation

A standard professional installation appointment typically takes about two hours to complete. Here’s what you can expect:

• Fiber Jack installation: Unless you already have a Fiber Jack installed, the technician installs the Fiber Jack, the small device that brings the GFiber optic signal into your home. If desired, you can consult with your tech on a preferred location for the Fiber Jack, and as long as it is feasible we’ll place it exactly where you want it.

• Equipment configuration: We connect and configure your GFiber Wi-Fi router and any included mesh extenders for whole-home coverage. We run a series of tests to make sure your Wi-Fi signal is strong, paying special attention to the highest use areas of your home. With Home and Edge, the technician may also take advantage of eligible existing home wiring to hard wire up to two of your highest use areas as well. 

• Performance verification: Your technician will run multiple speed and coverage tests as well as a battery of other diagnostics to confirm your connection is performing to GFiber’s high standards, ensuring we never leave a home that isn't running at its absolute best. This includes a specific check for symmetrical speeds. We don't just test your download; we verify your upload is just as strong so your connection is ready for high-stakes video calls or gaming the second we leave.

You can track your technician’s arrival in real time or manage your appointment details directly through the GFiber App.

Simple pricing with no equipment rental fees

We believe a great installation shouldn't come with a bill. While other providers might charge you a 'self-install' fee just to hand you a box, our setup is always free. From there, your pricing stays transparent. Your GFiber Fiber Jack and Wi-Fi router are included with your internet service, and you won’t be charged a monthly rental fee for the equipment you need to stay connected.