Tag: WebMCP

How Gemini Intelligence Will Reshape Search and Commerce

I see Google’s unveiling of Gemini Intelligence at the May 12 Android Show as a significant step toward an agent-powered future. Announced alongside a new laptop called the Googlebook, Gemini Intelligence is designed as an underlying layer that works across the Android operating system on laptops, phones, watches, and glasses.

The Googlebook makes that vision tangible to me. Built from the ground up around an AI agent, it can understand what is on the screen and act on it. I could point to a date in an email and have the agent schedule a meeting, or select furniture in an app and see how those pieces might look in my living room.

I believe this ability to complete tasks without requiring someone to open a webpage will fundamentally change how people search, discover information, and conduct commerce. Here is how I expect that shift to affect the search industry.

What the shift to an agentic operating system means

Until now, I have viewed search as a familiar sequence: someone has a question or intent, enters it into a search engine, receives a list of links, and chooses one. Earning a prominent position on that list was the prize, and much of the SEO industry was built around winning that click.

Gemini Intelligence starts from a very different assumption. Search intent still exists, but an AI agent can handle the steps between the request and the outcome. It can read pages, complete forms, and increasingly finish the entire task. Instead of visiting a website myself, I may have an agent visit and use it on my behalf.

When I look for an early example, Chrome Auto Browse stands out. Launched in January and built on Gemini 3, it can manage multistep tasks such as researching flights, filling out forms, scheduling appointments, and managing subscriptions. It then pauses for approval before making a purchase.

That efficiency gives me a clear reason to believe ecommerce will continue moving toward agentic AI.

A 2025 preprint supports this view. Researchers evaluated the declared-tools approach across online shopping, authentication, and content management. They found that giving an agent pre-structured interaction data reduced processing requirements by 67.6% and lowered costs by 34% to 63% compared with parsing a complete HTML document. Task success declined only slightly, from 98.8% with the traditional method to 97.9%.

The architecture behind Gemini Intelligence

To me, the architecture is as important as the interface. AI agents naturally favor websites they can interact with cleanly and efficiently, and Gemini Intelligence can only deliver on its promise if those agents can perform tasks reliably.

I see two protocols as central to making that possible. WebMCP turns a website’s actions into callable tools, while the Universal Commerce Protocol (UCP) allows an agent to complete a sale. Together, they enable an agent to finish a task without requiring a person to load and navigate the underlying webpage.

As AI reshapes search, every glowing path to discovery carries commercial value—turning SEO investment into a conversation about pipeline, risk, and customer acquisition costs.

WebMCP

I think of WebMCP as a labeled menu for AI agents. The API allows a website to declare functions as structured tools an agent can call, including searching inventory, beginning checkout, or submitting a support request.

Google co-developed WebMCP with Microsoft. An origin trial is live in Chrome 149, Firefox has committed to the third quarter of 2026, and Safari is expected to follow in the fourth quarter.

Universal Commerce Protocol (UCP)

I see UCP as the transactional counterpart to WebMCP. It gives AI agents a shared language for discovering products, building a cart, completing checkout, and managing orders without requiring someone to visit the merchant’s website.

Google also offers a consumer-facing layer called Universal Cart. It can collect items as I move across Search, Gemini, YouTube, and Gmail, creating a more connected shopping experience across Google’s products.

The range of companies behind UCP shows me how seriously the industry is taking this shift. Google, Shopify, Walmart, Target, Etsy, Wayfair, PayPal, and Stripe co-developed the protocol, which launched in January.

How I would prepare for agentic AI

My main takeaway is that websites are rapidly evolving from destinations into backends—from places people actively visit into systems agents quietly use. As the operating system becomes a search and action layer, I no longer think ranking is the only question that matters. I also need to ask whether an agent can actually use the site.

To prepare, I would begin by auditing the site’s most valuable actions, whether that means submitting a lead form, completing a booking flow, or reaching checkout. I would determine whether an agent could complete each action reliably and check the site’s Lighthouse Agentic Browsing score much as I would review Core Web Vitals. The goal is to understand whether an agent can use the site, not merely read it.

If I ran an ecommerce business, I would confirm whether the checkout process is accessible through UCP or ACP. I would also continue investing in retrieval and visibility because an agent still needs to find and trust the business before it can act on anyone’s behalf.

Dig deeper: Are we ready for the agentic web?

Inspired by this post on Search Engine Land.

July 10, 2026
How I Win the AI Decision Layer in Agentic Commerce

I see the next major battleground for brands being shaped by AI. Every day, AI engines and autonomous agents decide which brands to recommend, compare, cite, and transact with on behalf of consumers. To compete, I have to make my brand the trusted choice AI selects.

This shift is already underway. Adobe data shows that AI-referred traffic to U.S. retail websites grew 4,700% year over year through mid-2025. Salesforce reports that AI and autonomous agents influenced one in five online orders globally during Cyber Week, driving an estimated $67 billion in sales.

As AI becomes the interface between consumers and brands across discovery, evaluation, and purchase, I need to think beyond traditional rankings. A new competitive layer is emerging: the AI decision layer. This is where AI systems evaluate trust, relevance, authority, and transaction readiness before deciding which brands make the shortlist.

If I fail to influence this layer, my brand may be excluded before a customer ever sees it. That makes AI visibility, credibility, and actionability core parts of modern search strategy.

How I take a brand from found to actioned

Agentic commerce readiness follows a clear sequence. I start by making sure AI engines can find my brand, then I move through the remaining stages until AI agents can understand, trust, recommend, and transact with it.

Step 1: I get found by enabling AI discovery and access

Machine accessibility is the foundation of AI visibility. If I want AI systems to discover and access my brand, I have to prioritize technical hygiene and token efficiency.

I start by allowing the right crawlers on my website. Google, OpenAI, Anthropic, and Bing need to reach my content without unintended restrictions.

Then I get the basics right. I set up XML sitemaps and robots.txt, fix crawl errors, add canonical tags, and maintain strong Core Web Vitals. I also make sure my website content is rendered server-side so agents can reliably navigate and reason over my pages.

I also pay close attention to token efficiency. Bloated HTML wastes valuable tokens that AI systems could otherwise use to understand my content, products, and brand.

To make my site more AI-ready, I publish assets that help large language model crawlers process my content more efficiently. An llms.txt file can give LLM crawlers a concise map of my website, while Markdown versions of key content can reduce token consumption and improve machine understanding.

Dig deeper: The enterprise blueprint for winning visibility in AI search

Between consumers and brands, AI agents now act as the decision layer, handling discovery, evaluation, trust signals, and transactions before products reach the shortlist.

Step 2: I become understood by building semantic clarity

To be understood by AI engines, I need to build entity authority. This helps AI interpret who I am, what I offer, and why my brand matters.

Structured data turns my web pages into machine-readable knowledge that AI systems can understand, trust, and use. I strengthen my entity graph with comprehensive schema, trusted citations, and linked references.

I also deliver clean, server-rendered HTML that AI can access without friction. Semantic HTML, structured @graph IDs, and consistent naming help AI engines connect the right context to my brand.

Step 3: I get retrieved by structuring content for AI extraction

Traditional search ranks pages, but AI search retrieves and cites passages. That means I win on relevance, clarity, authority, and freshness rather than length alone. Original expertise, proprietary data, and real-world experience give my content a stronger chance of being selected.

To structure my content for retrieval, I use a clear heading hierarchy with H1, H2, and H3 tags. Under each heading, I create descriptive, self-contained sections that can stand on their own.

I build interconnected topic clusters instead of isolated pages because AI needs enough context to assemble complete answers.

I also front-load every section. I put the core answer and the most important metrics in the opening sentence before a model hits its token limit.

Dig deeper: Chunk, cite, clarify, build: A content framework for AI search

Step 4: I build trust with authority and grounding signals

Just because AI engines retrieve my content does not mean they will recommend my brand. Retrieval is only one step. Trust is what moves a brand closer to selection.

AI systems prioritize sources they can trust, so authority and credibility become decisive. Google’s experience, expertise, authoritativeness, and trustworthiness principles, known as E-E-A-T, remain some of the strongest signals influencing whether a brand is cited, referenced, or selected.

A visual roadmap for becoming the brand AI selects: first be found and understood, then retrieved, trusted, chosen and finally actioned by autonomous assistants.

Trust extends far beyond my website. AI evaluates review sentiment, location accuracy, pricing consistency, product availability, and entity alignment across the web. When those signals conflict, AI confidence decreases.

Credibility is now computational. Grounding, the process of validating responses against trusted evidence, is the bridge between visibility and recommendation.

To earn computational trust, I create original, expert-driven content that shows real experience and unique value. Then I align every external signal so reviews, listings, maps, and directories all tell one consistent story about my brand.

Dig deeper: Integrating SEO into omnichannel marketing for seamless engagement

Step 5: I get chosen by earning machine and human preference

AI agents parse attributes, verify claims, and score confidence in milliseconds. If I cannot make my value clear to AI, my brand becomes invisible at the decision point.

But emotional preference still matters. Consumers may delegate routine purchases, yet they hold tightly to choices tied to identity. The strongest brands optimize for both machine readability and human resonance.

To earn AI recommendations, I measure AI visibility, citation, and recommendation rates through query fan-out testing. I keep brand, product, and location data consistent across every channel. I also work to earn trusted mentions and references that strengthen AI confidence in my brand.

Dig deeper: How to boost your marketing revenue with personalization, connectivity, and data

Step 6: I enable agentic transactions

Recommendation is no longer the finish line for AI search. Discovery, selection, and checkout can now happen inside an AI assistant without the customer ever visiting my site.

An agentic website is designed for AI agents to discover information, retrieve answers, and perform actions on behalf of users. NLWeb helps make website content conversational and machine-readable, improving how AI systems find and understand the site.

A bold Google logo sits atop layered, colorful digital documents, evoking the fast-moving world of search marketing, ad formats, campaign assets, and platform updates.

Web Model Context Protocol, or MCP, extends this capability by giving AI agents a standardized way to interact with website functions. That can include retrieving data, initiating workflows, and submitting forms.

Agentic commerce moves the full transaction inside the assistant. Google’s Universal Commerce Protocol, or UCP, enables chat-based bookings. OpenAI and Stripe’s Agentic Commerce Protocol, or ACP, pushes inventory so AI systems can surface it more easily. Agent Payments Protocol, or AP2, then lets the agent pay.

Underneath these capabilities is MCP, which enables an LLM to read products, content, and live data. This changes my website from a destination into a source of truth. It supplies the inventory, pricing, and signals that drive every agent journey.

Dig deeper: How to select a CMS that powers SEO, personalization, and growth

How I measure performance in the AI decision layer

I still track traditional search metrics like rankings, sessions, and clicks. They remain useful, but they are no longer enough to measure success in AI search and agentic commerce.

For visibility, I track AI presence rate, AI share of voice, citation frequency, and agent recommendation rate.

For commerce, I track AI-influenced revenue, agent conversion rate, autonomous transaction volume, and agentic wallet share.

I also expect traffic patterns to change. Direct visits may decline as agents handle discovery, but AI-influenced transactions through machine-readable layers like WebMCP and schema endpoints can offset that loss and create new revenue paths.

With these changes in place, my website can become the trusted source AI systems rely on for both information and action.

From SEO to decision architecture

SEO remains the foundation for winning search, but a deeper shift became concrete at Google I/O 2026. AI agents now parse raw HTML, distill the browser’s native accessibility tree, and capture visual screenshots through vision models.

Together, these three paths determine whether a site is truly actionable for AI. My page can be technically flawless and still fail if its structure, semantics, or user experience breaks the chain. If I miss any stage, trust and transaction readiness suffer.

When I get these pieces right, my brand becomes discoverable, understandable, trusted, and transactable when AI agents make decisions. The brands that build these capabilities today will be the brands AI surfaces, trusts, and recommends tomorrow.

Inspired by this post on Search Engine Land.

July 9, 2026
Why Preparing for WebMCP Now is Crucial for SEO Success

I’ve seen many technologies come and go throughout my career. I used to chase after every new trend, trying to stay on the cutting edge. However, I quickly learned that this approach often cost me and my clients countless hours, with many technologies fading into obscurity. Does anyone remember Google Authorship?

I’ve realized that by waiting for wider adoption, learning from early adopters’ mistakes, and catching up quickly, I avoid wasting time and create more value. This approach has been invaluable to me.

However, some moments in technological advancement stand out—when being an early mover means not just succeeding but helping shape the future. The first people to realize the importance of PageRank and started building links can relate. WebMCP feels like another one of those pivotal moments, only larger.

The change we’re facing isn’t just about search engine mechanics or generative engine visibility. Discovery itself is evolving, and the entities performing this discovery are changing too.

I remember the age-old debate in SEO circles—should we focus on search engines or people? My answer is both. Yet now, this paradigm is shifting. What happens when discovery shifts from human-driven to being guided by AI agents?

When you ask ChatGPT a question today, it processes information, conducts additional searches, asks follow-ups, and delivers conclusions. The AI agent plans and decides for you, influenced entirely by its data sources and interpretive frameworks.

This evolution represents just one chapter in the ongoing story of discovery:

Discovery v1: Experiential interactions and word of mouth dominated.

Discovery v2: The written word took prominence in libraries and print media.

Discovery v3: The web spawned directories and search engines.

Discovery v4: Today, we see AI and LLMs increasingly aid discovery.

Discovery v5 (coming soon): Agentic systems will advance to perform actions autonomously.

Embracing Discovery v5 could offer us significant liberation—freeing our minds from mundane decisions, and enabling a focus on what truly matters.

The path to Trustable AI is underway. I now trust AI systems with everyday queries, relying on them more each time they enhance their capabilities.

Would I trust an AI to handle complex tax or health questions? Not entirely. Would I ask it to help plan dinner or schedule my day? Definitely.

This gradual trust expansion parallels past experiences with technology. As it grows, so does our reliance on agents to act on our behalf.

The tangible impact is visible: Automating grocery reorders or offering extraordinary travel deals are low-risk, high-reward changes.

The skepticism towards relinquishing control to technology is as old as technology itself. From fear of entering credit card details online to today’s reliance on smartphones and GPS, each shift was gradual but unstoppable.

WebMCP, which facilitates AI interaction with websites, is a browser-native web standard. It’s gaining momentum, authored by Google and Microsoft. It’s about easing AI’s job in understanding actions on websites, not replacing human interaction.

AI doesn’t need to infer tasks. WebMCP allows clear communication of a site’s capabilities, marking a shift like early schema markup days.

Engaging with this framework ensures your site is AI-ready, simplifying AI interaction.

WebMCP impacts discovery, influencing which sites AI agents prefer. Having your site AI-visible can make or break engagement in the emerging landscape of Discovery v5.

I’m taking advantage of this moment, despite my usual skepticism of early adoption—it feels different this time.

Inspired by this post on Search Engine Land.

May 15, 2026
Unlocking WebMCP: AI’s Key to Seamless Web Interaction with Chrome
Recently, while exploring the latest developments in web technology, I stumbled upon something groundbreaking: WebMCP, introduced in Chrome 146. Being a tech enthusiast, I was intrigued to learn how this emerging protocol could reshape the way AI agents interact with websites.

Chrome 146 has rolled out an exciting early preview of WebMCP, hidden behind a flag. This protocol, known as Web Model Context Protocol (WebMCP), is designed as a web standard to lay out website tools in a structured manner, guiding AI agents in executing tasks seamlessly.

So, what does this mean for us? Historically, the internet has been developed with humans in mind. Buttons, forms, and dropdowns are all elements we understand. But there’s an emerging user—AI agents. Soon, they will be completing registrations, purchasing tickets, and achieving other goals autonomously on websites.

Currently, AI agents face a daunting task. They navigate websites by crawling and attempting to decipher their functionalities. Imagine an AI agent trying to book a flight. It has to identify input fields, guess data formats, and pray nothing goes awry. It’s far from ideal.

The introduction of WebMCP is set to change this. By exposing the structure behind web tools, AI agents will be equipped to understand and execute tasks with ease.

Let’s dive a bit deeper to understand WebMCP. Picture yourself needing to book a flight.

Without WebMCP: An AI agent scrambles to find a relevant button like “Book a Flight” or “Search Flights.” It then interprets the on-screen information, hoping it inputs correctly.

With WebMCP: Forget searching for buttons. Instead, the agent calls a function, like bookFlight(), using well-defined parameters (such as date, origin/destination, and passengers), receiving a structured result in return. Much like developers interacting via APIs, AI agents will seamlessly call functions.

WebMCP empowers websites with JavaScript APIs and HTML form annotations, guiding AI agents on interacting with web tools in three steps:

Discovery: What tools does the page support? Examples include Checkout, BookFlight, or searchProducts.

JSON Schemas: They precisely define expected inputs and the kind of output that will be returned.

State: Tool availability alters based on the page’s state, allowing agents to only see actions relevant to the current context.

My website, for instance, could offer a list of actions each detailing its functionality, accepted inputs, returned outputs, and required permissions.

But why does this matter? AI agents are infiltrating our daily workflows rapidly. Soon, AI will handle our flight bookings, fill out forms, and publish content. But, as of now, AI agents struggle to interact seamlessly with websites due to two current approaches:

Automation (fragile): An AI acts by clicking buttons and inputting data like we do, but since websites frequently update, this can lead to failures.

APIs (limited): While APIs offer a structured approach for interaction, they’re not universally available or comprehensive.

WebMCP offers a middle ground, allowing websites to make tools accessible without the drawbacks of UI automation or needing separate APIs.

Like the early 2000s SEO race, WebMCP symbolizes a shift towards optimization for AI agents. Those who adopt this early could enjoy significant advantages as AI-centric search and commerce grow.

This opportunity is not merely about SEO anymore. It’s about realizing broader growth potential through WebMCP, which signifies not just being discoverable, but actionable by AI agents who’ll soon connect with future customers.

Practical applications of WebMCP in B2B and B2C scenarios are vast, from simplifying quote requests to expediting inventory checks, offering a seamless experience for business and everyday consumers alike.

To start experimenting with WebMCP, Chrome 146 lets you access it behind a feature flag. It’s still in its nascent stage but provides a valuable chance for developers and innovative teams to play around with the conceptual framework.

While getting acquainted with WebMCP, you’ll need Chrome version 146.0.7672.0 or later and a basic understanding of Chrome flags. Follow these steps to set up:
- Navigate to chrome://flags/#enable-webmcp-testing in Chrome.
- Set the “WebMCP for testing” flag to “Enabled”.
- Relaunch Chrome.
Start experimenting with WebMCP today and perhaps even install the Model Context Tool Inspector Extension to witness WebMCP in action. It’s an exciting era we’re stepping into, enabling websites to be as understandable to AI as they are to us.

Inspired by this post on Search Engine Land.
March 4, 2026