logo
The battle to AI-enable the web: NLweb and what enterprises need to know

The battle to AI-enable the web: NLweb and what enterprises need to know

Business Mayor26-05-2025
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More
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.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Made by Google 2025: We Found All the Biggest Pixel 10 Leaks and Rumors
Made by Google 2025: We Found All the Biggest Pixel 10 Leaks and Rumors

CNET

timean hour ago

  • CNET

Made by Google 2025: We Found All the Biggest Pixel 10 Leaks and Rumors

The new Pixel 10 line will debut on Aug. 20 at the Made by Google event, and it almost feels like the phones have been revealed in detail thanks to a multitude of rumors and presumed leaks. Google itself isn't hiding that the Pixel 10 is coming, posting multiple looks of the phone when promoting the upcoming announcement, but the company is still keeping detailed specs and features of the Pixel 10 line to itself. If we follow the series of rumors, though, several recent details suggest a lot of new life to the phone line. While we do expect the Pixel line to continue the overall lineup of the Pixel 9 -- including a base Pixel 10, Pixel 10 Pro, Pixel 10 Pro XL and Pixel 10 Pro Fold -- rumors are pointing to significant changes to what's inside these phones to make them more feature-packed than ever. We've rounded up the biggest rumors we've found so far about the Pixel 10 line here, and will continue updating as we hear more ahead of the Aug. 20 event. Now Playing: Google Pixel 10 Revealed in Promo, iOS 26 Public Beta to Open, and More | Tech Today 03:16 Pixel 10, 10 Pro and 10 Pro XL's release date, pricing and cameras Starting with the three non-folding phones in the Pixel 10 line that are getting revealed on Aug. 20, we expect the Pixel 10, Pixel 10 Pro and Pixel 10 Pro XL to look similar to the Pixel 9 line on the outside. This includes the same rounded camera bar on the back. The entry-level Pixel 10 will get a brand new third rear camera. While we can see the third camera in the photos Google posted of the Pixel 10, according to a chart posted by known leaker Evan Blass, this will be a 10.8-megapixel telephoto camera that will join a 48-megapixel wide-angle camera and a 13-megapixel ultrawide. This will help the Pixel 10 compare better with the base Galaxy S25, which also has a telephoto camera. The 10 Pro and 10 Pro XL will continue to be differentiated from the standard Pixel 10 with a higher-specced camera system, which includes a 50-megapixel wide-angle, 48-megapixel ultrawide and a 48-megapixel telephoto, according to the same chart posted by Blass. The colors for the Pixel 10 and Pixel 10 Pro phones also appear to have leaked, with Android Headlines reporting that the base Pixel 10 will come in Obsidian, Indigo, Frost and Lemonade editions. These names would roughly correspond to a black, blueish purple, light blue and yellow colors, respectively. The Pro models will also come in four colors, with Android Headlines reporting models named Obsidian, Porcelain, Moonstone and Jade. Those should roughly match up to black, white, gray and a light green. More photos of these phones were posted by Blass, purporting to be the Pixel 10 lineup from the front, back and side profiles Despite the concerns with tariffs, the Pixel 10 line is rumored to keep the same starting prices as the Pixel 9 line. Pixel 10 line rumored prices Phone Storage US Price Pixel 10 128GB $799 Pixel 10 256GB $899 Pixel 10 Pro 128GB $999 Pixel 10 Pro 256GB $1,099 Pixel 10 Pro 512GB $1,219 Pixel 10 Pro 1TB $1,449 Pixel 10 Pro XL 256GB $1,199 Pixel 10 Pro XL 512GB $1,319 Pixel 10 Pro XL 1TB $1,549 The Samsung Galaxy S25 Ultra inside of a magnetic case, with a wallet accessory attached. Celso Bulgatti/CNET Pixel 10 could support Qi2 magnetic charging The Pixel 10 series could support magnetic accessories, making it one of the few Android phones that would work with many of the MagSafe accessories that were first built to work with Apple's iPhone. That's because the Pixel 10 is rumored to fully support Qi2 wireless charging, which supports magnetic alignment and has magnets built into the phone without needing a case. An image posted by Blass appears to show a Pixel 10 with a circular wireless charger attached to the back, likely using magnets similar to how MagSafe works with the iPhone. If this is the case, it's a huge step for the Qi2 wireless standard, as the only other Android phone so far that supports magnetic accessories is the HMD Skyline. This would allow the Pixel 10 series to natively work with magnetic phone chargers, wallets, mounts and other accessories. Google might also create its own branding for this feature, as an Android Authority report claims that official Pixel 10 accessories that magnetically attach would be called PixelSnap. If this comes true, it would also make it easier to swap accessories between the iPhone and the Pixel. In addition to the iPhone's support for charging over USB-C, this would mean that MagSafe accessories first purchased to use with an iPhone should work just as well when swapping over to a Pixel 10 phone. The Pixel 9 includes the Tensor G4 processor, and its successor for the Pixel 10 is reportedly made by TSMC. James Martin/CNET Google's Tensor G5 chip Following last year's Tensor G4 chip in the Pixel 9 lineup, we presume that the Pixel 10 phones will be powered by a (supposedly named) Tensor G5 chip. We've heard a few Tensor G5 rumors, including that it will be made on an industry-standard 3nm process by chip fabricator TSMC, according to an Android Authority March report. Other rumors are less promising, like a July report from WCCFTech suggesting that while the Tensor G5 is a significant upgrade on last year's Tensor G4, a leaked benchmark test claims it will run slower than the Snapdragon 8 Elite processor that's used in Samsung's Galaxy S25 line and the OnePlus 13. That Qualcomm processor might also soon be surpassed by the next Qualcomm silicon coming at Snapdragon Summit in September. That's not to imply the phone itself will perform slowly, as the same report says it will run faster than the Snapdragon 8 Gen 3 processor that powers Whether the Tensor G5 lags behind other mobile chips isn't as worrying as it might seem, since the Tensor chips are built for Google's Pixel devices -- and those don't seem to be underperforming in daily use. As CNET Editor-at-Large Andy Lanxon said about the Tensor G4 powering the Pixel 9 Pro XL, "On the one hand, it's disappointing not to see more of a tangible improvement over the predecessor. On the other hand, it doesn't feel like it's lacking in power in any major way." The Pixel 10 Pro Fold is presumed to have a similar look to the Pixel 9 Pro Fold (pictured here), but include the newer processor. James Martin/CNET Pixel 10 Pro Fold There aren't many rumors pointing toward another Pixel Fold, but it's always possible that Google surprises us with a big reveal of another version of its foldable phone line. The most recent, last year's Pixel 9 Pro Fold, not only switched up its nomenclature to fit into that year's standard Pixel lineup, but also altered its design from the wider passport-size original Pixel Fold to a taller, narrower format similar to other foldables like the Samsung Galaxy Z Fold 7. One Pixel 10 Pro Fold rumor from WCCFTech only shared details about the supposed Tensor chip powering it. But a recent rumor from Blass suggests we could expect the usual upgrades: a new Tensor G5 chip, perhaps slight spec upgrades and maybe even similar camera or battery upgrades if they are announced for the Pixel 10 lineup. The Pixel 10 Pro Fold would presumably get Android 16 out of the box, but since that software upgrade has already been released early (mere weeks after Google I/O 2025), last year's Pixel 9 Pro Fold already has that update anyway. We'll keep updating this roundup as we get closer to Google's Aug. 20 event for the Pixel 10 series.

Amazon-Backed (AMZN) Anthropic Just Announced a Big Upgrade
Amazon-Backed (AMZN) Anthropic Just Announced a Big Upgrade

Business Insider

timean hour ago

  • Business Insider

Amazon-Backed (AMZN) Anthropic Just Announced a Big Upgrade

Amazon-backed (AMZN) Anthropic is making a big upgrade to its Claude Sonnet 4 AI model by increasing the context window for enterprise API customers to one million tokens. For context, that is enough to handle about 750,000 words and 75,000 lines of code. This is a major jump from the previous 200,000 token limit and more than double OpenAI's GPT-5, which offers 400,000 tokens. The new long-context feature will also be available through Anthropic's cloud partners, including Amazon's Bedrock and Google (GOOGL) Cloud's Vertex AI. Elevate Your Investing Strategy: Take advantage of TipRanks Premium at 50% off! Unlock powerful investing tools, advanced data, and expert analyst insights to help you invest with confidence. This comes as OpenAI's new GPT-5 model offers lower pricing and high coding performance. Nevertheless, Anthropic's product lead, Brad Abrams, says that he is pleased with the firm's API growth and expects the longer context to bring 'a lot of benefit' to coding platforms. Interestingly, unlike OpenAI, which earns most of its revenue from ChatGPT subscriptions, Anthropic focuses on selling AI through APIs, which makes developer-focused platforms critical to its business. The company also recently updated its largest model, Claude Opus 4.1, to improve its coding capabilities. It is worth noting that having a larger context window can make AI far better at tasks like software engineering, where seeing the entire project leads to more accurate results. Abrams said that it also improves Claude's ability to work on 'agentic' coding tasks, which are complex problems that require the AI to keep track of its steps over minutes or hours. In addition, for API users sending prompts over 200,000 tokens, costs will rise to $6 per million input tokens and $22.50 per million output tokens, up from $3 and $15, respectively. What Is the Price Target for AMZN Stock? Turning to Wall Street, analysts have a Strong Buy consensus rating on Amazon stock based on 43 Buys and one Hold assigned in the past three months. Furthermore, the average AMZN stock price target of $264.40 per share implies 19.1% upside potential from current levels.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store