
The battle to AI-enable the web: NLweb and what enterprises need to know
In the first generation of the web, back in the late 1990s, search was okay but not great, and it wasn't easy to find things. That led to the rise of syndication protocols in the early 2000s, with Atom and RSS (Really Simple Syndication) providing a simplified way for website owners to make headlines and other content easily available and searchable.
In the modern era of AI, a new group of protocols is emerging to serve the same basic purpose. This time, instead of making sites easier for humans to find, it's all about making websites easier for AI. Anthropic's Model Control Protocol (MCP), Google's Agent2Agent and large language models/ LLMs.txt are among the existing efforts.
The newest protocol is Microsoft's open-source NLWeb (natural language web) effort, which was announced during the Build 2025 conference. NLWeb is also directly linked to the first generation of web syndication standards, as it was conceived and created by RV Guha, who helped create RSS, RDF (Resource Description Framework) and schema.org.
NLWeb enables websites to easily add AI-powered conversational interfaces, effectively turning any website into an AI app where users can query content using natural language. NLWeb isn't necessarily about competing with other protocols; rather, it builds on top of them. The new protocol uses existing structured data formats like RSS, and each NLWeb instance functions as an MCP server.
'The idea behind NLWeb is it is a way for anyone who has a website or an API already to very easily make their website or their API an agentic application,' Microsoft CTO Kevin Scott said during his Build 2025 keynote. 'You really can think about it a little bit like HTML for the agentic web.'
NLWeb transforms websites into AI-powered experiences through a straightforward process that builds on existing web infrastructure while leveraging modern AI technologies.
Building on existing data: The system begins by leveraging structured data that websites already publish, including markup, RSS feeds and other semi-structured formats that are commonly embedded in web pages. This means publishers don't need to rebuild their content infrastructure completely.
Data processing and storage: NLWeb includes tools for adding this structured data to vector databases, which enable efficient semantic search and retrieval. The system supports all major vector database options, allowing developers to choose the solution that best fits their technical requirements and scale.
Read More Building a 'virtual Vegas' in honor of CES
AI enhancement layer: LLMs then enhance this stored data with external knowledge and context. For instance, when a user queries about restaurants, the system automatically layers on geographic insights, reviews and related information by combining the vectorized content with LLM capabilities to provide comprehensive, intelligent responses rather than simple data retrieval.
Universal interface creation: The result is a natural language interface that serves both human users and AI agents. Visitors can ask questions in plain English and receive conversational responses, while AI systems can programmatically access and query the site's information through the MCP framework.
This approach allows any website to participate in the emerging agentic web without requiring extensive technical overhauls. It makes AI-powered search and interaction as accessible as creating a basic webpage was in the early days of the internet.
There are a lot of different protocols emerging in the AI space; not all do the same thing.
Google's Agent2Agent , for example, is all about enabling agents to talk to each other. It's about orchestrating and communicating agentic AI and is not particularly focused on AI-enabling existing websites or AI content. Maria Gorskikh, founder and CEO of AIA and a contributor to the Project NANDA team at MIT, explained to VentureBeat that Google's A2A enables structured task passing between agents using defined schemas and lifecycle models.
'While the protocol is open-source and model-agnostic by design, its current implementations and tooling are closely tied to Google's Gemini stack — making it more of a backend orchestration framework than a general-purpose interface for web-based services,' she said.
Another emerging effort is LLMs.txt. Its goal is to help LLMs better access web content. While on the surface, it might sound somewhat like NLWeb, it's not the same thing.
'NLWeb doesn't compete with LLMs.txt; it is more comparable to web scraping tools that try to deduce intent from a website,' Michael Ni, VP and Principal Analyst at Constellation Research told VentureBeat.
Krish Arvapally, co-founder and CTO of Dappier, explained to VentureBeat that LLMs.txt provides a markdown-style format with training permissions that helps LLM crawlers ingest content appropriately. NLWeb focuses on enabling real-time interactions directly on a publisher's website. Dap pier has its own platform that automatically ingests RSS feeds and other structured data, then delivers branded, embeddable conversational interfaces. Publishers can syndicate their content to their data marketplace.
MCP is the other big protocol, and it is increasingly becoming a de facto standard and a foundational element of NLWeb. Fundamentally, MCP is an open standard for connecting AI systems with data sources. Ni explained that in Microsoft's view, MCP is the transport layer, where, together, MCP and NLWeb provide the HTML and TCP/IP of the open agentic web.
Forrester Senior Analyst Will McKeon-White sees a number of advantages for NLWeb over other options.
'The main advantage of NLWeb is better control over how AI systems 'see' the pieces that make up websites, allowing for better navigation and more complete understanding of the tooling,' McKeon-White told VentureBeat. 'This could reduce both errors from systems misunderstanding what they're seeing on websites, as well as reduce interface rework.'
Microsoft didn't just throw NLWeb over the proverbial wall and hope someone would use it.
Microsoft already has multiple organizations engaged and using NLWeb, including Chicago Public Media, Allrecipes, Eventbrite, Hearst (Delish), O'Reilly Media, Tripadvisor and Shopify.
Andrew Odewahn, Chief Technology Officer at O'Reilly Media is among the early adopters and sees real promise for NLWeb.
'NLWeb leverages the best practices and standards developed over the past decade on the open web and makes them available to LLMs,' Odewahn told VentureBeat. 'Companies have long spent time optimizing this kind of metadata for SEO and other marketing purposes, but now they can take advantage of this wealth of data to make their own internal AI smarter and more capable with NLWeb.'
In his view, NLWeb is valuable for enterprises both as consumers of public information and publishers of private information. He noted that nearly every company has sales and marketing efforts where they might need to ask, 'What does this company do?' or 'What is this product about?'
'NLWeb provides a great way to open this information to your internal LLMs so that you don't have to go hunting and pecking to find it,' Odewahn said. 'As a publisher, you can add your own metadata using schema.org standard and use NLWeb internally as an MCP server to make it available for internal use.'
Using NLWeb isn't necessarily a heavy lift, either. Odewahn noted that many organizations are probably already using many of the standards NLWeb relies on.
'There's no downside in trying it out now since NLWeb can run entirely within your infrastructure,' he said. 'It's open source software meeting the best in open source data, so you have nothing to lose and a lot to gain from trying it now.'
Constellation Research Analyst Michael Ni has a somewhat positive viewpoint on NLWeb. However, that doesn't mean enterprises need to adopt it immediately.
Ni noted that NLWeb is in the very early stages of maturity and enterprises should expect 2-3 years for any substantial adoption. He suggests that leading-edge companies with specific needs, such as active marketplaces, can look to pilot with the ability to engage and help shape the standard.
'It's a visionary specification with clear potential, but it needs ecosystem validation, implementation tooling, and reference integrations before it can reach mainstream enterprise pilots,' Ni said.
Others have a somewhat more aggressive viewpoint on adoption. Gorskikh suggests taking an accelerated approach to ensure your enterprise doesn't fall behind.
'If you're an enterprise with a large content surface, internal knowledge base, or structured data, piloting NLWeb now is a smart and necessary step to stay ahead,' she said. 'This isn't a wait-and-see moment — it's more like the early adoption of APIs or mobile apps.'
That said, she noted that regulated industries need to tread carefully. Sectors like insurance, banking and healthcare should hold off on production use until there's a neutral, decentralized verification and discovery system in place. There are already early-stage efforts addressing this — such as the NANDA project at MIT that Gorskikh participates in, which is building an open, decentralized registry and reputation system for agentic services.
For enterprise AI leaders, NLWeb is a watershed moment and a technology that should not be ignored.
AI is going to interact with your site, and you need to AI enable it. NLWeb is one way that will be particularly attractive to publishers, much like RSS became a must-have for all websites in the early 2000s. In a few years, users will just expect it to be there; they will expect to be able to search and find things, while agentic AI systems will need to be able to access the content as well.
That's the promise of NLWeb.

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
an hour ago
- Yahoo
Anthropic says some Claude models can now end ‘harmful or abusive' conversations
Anthropic has announced new capabilities that will allow some of its newest, largest models to end conversations in what the company describes as 'rare, extreme cases of persistently harmful or abusive user interactions.' Strikingly, Anthropic says it's doing this not to protect the human user, but rather the AI model itself. To be clear, the company isn't claiming that its Claude AI models are sentient or can be harmed by their conversations with users. In its own words, Anthropic remains 'highly uncertain about the potential moral status of Claude and other LLMs, now or in the future.' However, its announcement points to a recent program created to study what it calls 'model welfare' and says Anthropic is essentially taking a just-in-case approach, 'working to identify and implement low-cost interventions to mitigate risks to model welfare, in case such welfare is possible.' This latest change is currently limited to Claude Opus 4 and 4.1. And again, it's only supposed to happen in 'extreme edge cases,' such as 'requests from users for sexual content involving minors and attempts to solicit information that would enable large-scale violence or acts of terror.' While those types of requests could potentially create legal or publicity problems for Anthropic itself (witness recent reporting around how ChatGPT can potentially reinforce or contribute to its users' delusional thinking), the company says that in pre-deployment testing, Claude Opus 4 showed a 'strong preference against' responding to these requests and a 'pattern of apparent distress' when it did so. As for these new conversation-ending capabilities, the company says, 'In all cases, Claude is only to use its conversation-ending ability as a last resort when multiple attempts at redirection have failed and hope of a productive interaction has been exhausted, or when a user explicitly asks Claude to end a chat.' Anthropic also says Claude has been 'directed not to use this ability in cases where users might be at imminent risk of harming themselves or others.' When Claude does end a conversation, Anthropic says users will still be able to start new conversations from the same account, and to create new branches of the troublesome conversation by editing their responses. 'We're treating this feature as an ongoing experiment and will continue refining our approach,' the company says. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

Business Insider
an hour ago
- Business Insider
Here's why Google might have to sell Chrome, and which companies want to buy it
Chrome is the world's most popular web browser. But how much longer it belongs to Google is an open question. A court last year ruled that Google had violated antitrust laws by maintaining a monopoly on internet search. A second ruling in April found Google also monopolized open-web digital ad markets. The Justice Department asked a judge to force Google to divest its premier web browser to remedy the case. A court is expected to rule on that by the end of this month. Chrome, a free web browser developed by Google, is an important distribution tool for Google Search and its other services. It also provides insights into users' search habits and is the most popular web browser on the market. Being forced to sell Chrome would be an undeniable blow to Google and its parent company, Alphabet Inc. Analysts at Barclays said such an action could be a black swan scenario for Google stock, sparking an estimated 15% to 25% decline. Google denies it's a monopoly. It said in a blog post in May that offloading the web browser to another party could render it "obsolete" and "expose billions of people to cyber-attacks." Although the judge has not yet decided Chrome's ultimate fate, competitors are already lining up to gladly take it off Google's hands. an AI search chat platform, confirmed to Business Insider that it made a $35 billion bid for Chrome this week. JP Morgan and several private equity firms backed the bid. is a division of the digital marketing company Public Good, which acquired in July. Public Good President Melissa Anderson and CEO Danny Bibi told Business Insider they reached out to Google on Wednesday. "Given the number of worldwide users Chrome has, it's a really just phenomenal way to scale user adoption," Anderson said. The pair said they're committed to using AI ethically, which means offering its search for free in an effort to make knowledge accessible for all. They also said founded in 1998, already has a network of clients, so finding potential advertisers wouldn't be a heavy lift. Perplexity Perplexity, an AI search startup, made a $34.5 billion bid for the web browser this week. The company launched an AI-native browser, Comet, in July. Although the bid is higher than Perplexity's entire valuation, The Wall Street Journal reported that several investors have agreed to back the potential deal. Perplexity said it would continue supporting Chromium, Google's open-source web browser project that's the foundation of Chrome, as part of the deal, according to the outlet. The outlet reported that Perplexity would continue to keep Google as the default search engine, but users could change that through settings. OpenAI Although OpenAI's ChatGPT turned it into the leading AI startup in Silicon Valley, the company is a tiny fraction of the size of a Big Tech mammoth like Google. Purchasing Chrome, however, would help even the playing field. During Google's antitrust hearing in April, OpenAI's head of ChatGPT testified that the company would be interested in acquiring Chrome if Google were forced to divest. "Yes, we would, as would many other parties," Nick Turley told the court, according to Bloomberg. OpenAI CEO Sam Altman also recently said he'd be interested in snapping up Chrome. "If Chrome is really going to sell, we should take a look at it," Altman told a group of journalists on Thursday, according to The Verge. Yahoo Yahoo, a direct competitor of Google, would also be interested in bidding on Chrome, Bloomberg reported. Brian Provost, the general manager for Yahoo Search, said Chrome is "arguably the most important strategic player on the web" during a hearing for Google's antitrust case in April. "We would be able to pursue it with Apollo," Provost said, referring to Yahoo's owner, Apollo Global Management Inc.


Buzz Feed
2 hours ago
- Buzz Feed
Amazon Echo Show 15: The Family Hub Worth Every Penny
Hi! I'm Sally Elshorafa — Home and Garden Editor here at BuzzFeed. I'm also someone who *loves* being organized, but would much rather adopt a great system than build one from scratch. I just like tools that fit into my life without me having to reinvent the wheel. Enter the Amazon Echo Show 15. It's a 15.6-inch full HD touchscreen display (try saying that three times fast), designed to be either wall-mounted like a piece of framed art or kept on a stand. Think Samsung's The Frame paired with Alexa's brains (oh no, is Alexa sentient?!?). It's slim, clean, and big enough to see from across the room, making it perfect for acting as a central hub in my busy home. And because it's voice-powered, I almost never have to touch it. I can control it entirely with my voice while I'm cooking, wrangling my children, or having a meltdown (often). Mine lives in the corner of our kitchen counter, because the kitchen is the most high-traffic spot in our house. In a multigenerational household like ours, placement is everything. Everyone sees it, everyone uses it, and that visibility is exactly what makes it work. It's not just another piece of tech bought under false pretenses; it's actually woven into the way we live. Cheesy, I know. of the best things about it is how customizable the display is. You can pin and arrange widgets so the things that matter most are always front and center. In our case, that's my family's shared Google Calendar (it works with Microsoft and Apple cals as well). We keep every appointment, meeting, school event, and trip on there, so there's no more, "Wait, you're in a meeting at the same time both kids have separate play dates scheduled?" surprises. The calendar on the Echo Show is in real time; if my husband updates it from his phone, it's instantly reflected on the screen in the kitchen. We also keep a synced shopping list on display, which anyone in our family can update through the Alexa app, or just by shouting out what needs to be added (a more common occurrence). If I notice we're out of eggs while making breakfast, I just say, "Alexa, add a dozen eggs to my shopping list." No pen, no paper, no unlocking my phone. Whoever ends up at the grocery store next sees the updated list immediately. And it's not just groceries. We add household items, kid stuff, and random things we think of mid-conversation. Right now, our list includes washing machine pods, extra pillowcases for the kids, and bulk cold brew. Once items are purchased, you can either check them off on the app or via the Echo Show, whatever works for you. Other widgets we use daily include a month-at-a-glance calendar (critical for planning ahead), a weather panel that updates in real time, curated news headlines based on our preferences, and a rotating photo carousel from a shared family album. The photo widget keeps it personal. You might be checking the calendar, but you're also catching glimpses of family vacations, silly toddler moments, and our favorite everyday snapshots. The smart home control panel is where the Echo Show 15 really earns its keep as a hub. Beyond organization and control, it's also an entertainment screen. It has built-in Fire TV, so I can stream Prime Video, Netflix, YouTube, and more directly on the display. Most of the time, I keep it in "mission control" mode, but sometimes I'll put on the local news while I'm making dinner, or watch an F1 race highlight while I stir a sauce that requires constant attention. Sorta random, but one thing I really like is that I can "drop in" via video to say hi to whoever is in the kitchen, which is great when one of us is out of town and wants to say hello to the kids. Using FaceTime works fine, but it's dependent on someone holding their phone up to others while everyone talks, which sucks if they're in the middle of doing something. Plus, phone screens are small. When I video chat on the Echo, it's a big, clear display, no hands required. The sound and volume are also better. This week alone, the Echo Show 15 has run three labeled timers while I was cooking an elaborate meal, played "Let It Go" from Frozen on command to end a toddler meltdown, warned me about an incoming afternoon rainstorm despite it being a heatwave so the kids could grab their raincoats on their way out, added oat milk to the shopping list mid-coffee pour, displayed a live baby monitor feed while I prepped lunch, let me know that my favorite baseball team got absolutely destroyed during an away game, and delivered a five-minute news update from NPR while I folded cloth napkins. None of these are flashy tech miracles, but together they make the day run more smoothly. The beauty of the Echo Show is that it doesn't require constant tinkering. You can display it horizontally or vertically — whatever works for you. Reviewers are split 50/50 on how they display it. Half mount it to the wall, the other put it on a stand. Some get really creative with how it's mounted, so it looks like it's part of a gallery wall. Some people mount it to their bathroom mirror. You can also display it vertically — it'll rotate the screen so everything still looks good. It also helps that the device is aesthetically pleasing. The clean design and slim bezel means it blends into the kitchen instead of looking like a big piece of tech taking up counter space. If I wanted to, I could mount it so it looks like framed art, but the stands works better for us since it's easier to move if we ever want to shift things around. The screen itself is bright and large enough to read from a distance, which is something smaller devices can't really match. Living in a multigenerational household means there's a constant flow of information, needs, and schedules to keep track of. The Echo Show has become the quiet extra set of hands that remembers what's running low, keeps track of where everyone needs to be, entertains when needed, and makes sure the important stuff doesn't slip through the cracks. I originally bought it on a whim, wondering if it would be one of those "will this make me the person I want to be?" purchases. Instead, it turned out to be something far from practical, a device that actually makes our daily life easier, keeps the whole family on the same page, and looks good doing it. It's not just another smart display. It's the nerve center of our home. And for a busy family like mine, that makes it worth every penny we spent on it. Get the Amazon Echo Show 15 from Amazon for $299.99.