The Requirements Powering The Agentic Net

This is Half 3 in a five-part collection on optimizing web sites for the agentic internet. Half 1 coated the evolution from search engine optimisation to AAIO. Half 2 explored how to get your content material cited in AI responses. This article goes deeper: the protocols forming the infrastructure layer that make every part else attainable.

The early internet wanted HTTP to transport knowledge, HTML to construction content material, and the W3C to preserve everybody constructing on the identical basis. With out these shared requirements, we’d have ended up with a fragmented assortment of incompatible networks as an alternative of a single internet.

The agentic web is at that very same inflection level. AI brokers want standardized methods to join to instruments, discuss to one another, question web sites, and perceive codebases. With out shared protocols, each AI vendor builds proprietary integrations, and the outcome is the identical fragmentation the early internet narrowly averted.

4 protocols are rising as the foundational layer. This article covers what every one does, who’s behind it, and what it means for your enterprise. All through this collection, we draw solely from official documentation, analysis papers, and bulletins from the corporations constructing this infrastructure.

Why Requirements Matter

Take into account how the authentic internet got here collectively. In the early Nineteen Nineties, competing browser distributors and incompatible requirements had been fragmenting what ought to have been a unified community. The W3C introduced order by establishing shared protocols. HTTP dealt with transport. HTML dealt with construction. Everybody agreed on the guidelines, and the internet took off.

AI is at an identical crossroads. Proper now, each main AI firm is constructing brokers that want to work together with external instruments, knowledge sources, different brokers, and web sites. With out requirements, connecting your enterprise programs to AI means constructing separate integrations for Claude, ChatGPT, Gemini, Copilot, and no matter comes subsequent. That’s the M x N drawback: M completely different AI fashions occasions N completely different instruments equals an unsustainable variety of customized connections.

What makes this second exceptional is who’s constructing the answer collectively. On Dec. 9, 2025, the Linux Basis announced the Agentic AI Foundation (AAIF), a vendor-neutral governance physique for agentic AI requirements. Eight platinum members anchor it: AWS, Anthropic, Block, Bloomberg, Cloudflare, Google, Microsoft, and OpenAI.

OpenAI, Anthropic, Google, and Microsoft. Competing on AI merchandise, collaborating on AI infrastructure. As Linux Basis Government Director Jim Zemlin put it: “We are seeing AI enter a brand new part, as conversational programs shift to autonomous brokers that may work collectively.”

This is a much bigger deal than most individuals notice. Opponents constructing shared infrastructure as a result of all of them acknowledge that proprietary requirements would maintain again the complete ecosystem, together with themselves.

MCP: The Common Adapter

What it is: The Model Context Protocol (MCP) is an open normal for connecting AI purposes to external instruments, knowledge sources, and workflows.

The official analogy is apt:

“Think of MCP like a USB-C port for AI applications. Simply as USB-C supplies a standardized means to join digital units, MCP supplies a standardized means to join AI purposes to external programs.”

Earlier than MCP, if you happen to needed your database, CRM, or inside instruments accessible to an AI assistant, you had to construct a customized integration for every AI platform. MCP replaces that with a single normal interface. Construct one MCP server in your knowledge, and each MCP-compatible AI system can join to it.

The numbers are hanging. MCP launched as an open-source challenge from Anthropic on Nov. 25, 2024. In simply over a yr, it reached 97 million monthly SDK downloads throughout Python and TypeScript, with over 10,000 public MCP servers constructed by the neighborhood.

The adoption timeline tells the story. Anthropic’s Claude had native MCP help from day one. In March 2025, OpenAI CEO Sam Altman announced help throughout OpenAI’s merchandise, stating: “Folks love MCP and we are excited to add help throughout our merchandise.” Google adopted in April, confirming MCP help in Gemini. Microsoft joined the MCP steering committee at Construct 2025 in Could, with MCP help in VS Code reaching general availability in July 2025.

From inside experiment to business normal in 12 months. That tempo of adoption indicators one thing actual.

What this implies for your enterprise: In case your knowledge, instruments, or providers are MCP-accessible, each main AI platform can use them. That’s not a theoretical profit. It means an AI assistant serving to your buyer can pull real-time product availability from your stock system, verify order standing from your CRM, or retrieve pricing from your database, all via one standardized connection fairly than platform-specific integrations.

A2A: How Brokers Discuss To Every Different

What it is: The Agent2Agent protocol (A2A) allows AI brokers from completely different distributors to uncover one another’s capabilities and collaborate on duties.

If MCP is how brokers join to instruments, A2A is how brokers join to one another. The excellence issues. In a world the place companies use AI brokers from Salesforce for CRM, ServiceNow for IT, and an inside agent for billing, these brokers want a means to uncover what one another can do, delegate duties, and coordinate responses. A2A supplies that.

Google launched A2A on April 9, 2025 with over 50 know-how companions. By June, Google donated the protocol to the Linux Foundation. By July, version 0.3 shipped with over 150 supporting organizations, together with Salesforce, SAP, ServiceNow, PayPal, Atlassian, Microsoft, and AWS.

The core idea is the Agent Card: a JSON metadata doc that serves as a digital enterprise card for brokers. Every A2A-compatible agent publishes an Agent Card at a standard web address (/.well-known/agent-card.json) describing its id, capabilities, abilities, and authentication necessities. When one agent wants assist with a process, it reads one other agent’s card to perceive what that agent can do, then communicates via A2A to request collaboration.

Google’s personal framing of how these items match collectively is helpful: “Build with ADK, equip with MCP, communicate with A2A.” ADK (Agent Growth Package) is Google’s framework for constructing brokers, MCP offers them entry to instruments, and A2A lets them discuss to different brokers.

Right here’s a sensible instance. A buyer contacts your organization with a billing query that requires a refund. Your customer support agent (constructed on one platform) identifies the difficulty, passes the context to your billing agent (constructed on one other platform) through A2A, which calculates the refund quantity and palms off to your funds agent (yet one more platform) to course of it. The client sees one seamless interplay. Behind the scenes, three brokers from completely different distributors collaborated via a shared protocol.

The enterprise adoption sign is robust. When Salesforce, SAP, ServiceNow, and each main consultancy signal on to a protocol inside months, it’s as a result of their enterprise purchasers are already working into the multi-vendor agent coordination drawback that A2A solves.

NLWeb: Making Web sites Conversational

What it is: NLWeb (Pure Language Net) is an open challenge from Microsoft that turns any web site right into a pure language interface, queryable by each people and AI brokers.

Of the 4 protocols coated right here, NLWeb is the most immediately related to this collection’ viewers. MCP, A2A, and AGENTS.md are primarily developer considerations. NLWeb is about your web site.

NLWeb was introduced at Microsoft Build 2025 on Could 19, 2025. It was conceived and developed by R.V. Guha, who joined Microsoft as CVP and Technical Fellow. If that title sounds acquainted, it ought to: Guha is the creator of RSS, RDF, and Schema.org, three requirements that basically formed how the internet organizes and syndicates information. When the particular person behind Schema.org builds a brand new internet protocol, it’s value paying consideration.

The important thing perception behind NLWeb is that web sites already publish structured knowledge. Schema.org markup, RSS feeds, product catalogs, recipe databases. NLWeb leverages these present codecs, combining them with AI to let customers and brokers question a web site’s content material utilizing pure language as an alternative of clicking via pages.

Microsoft’s framing is deliberate: “NLWeb can play a similar role to HTML in the emerging agentic web.” The NLWeb README places it much more immediately: “NLWeb is to MCP/A2A what HTML is to HTTP.”

Each NLWeb occasion is robotically an MCP server. Meaning any web site working NLWeb instantly turns into accessible to the complete ecosystem of MCP-compatible AI assistants and brokers. Your web site’s content material doesn’t simply sit there ready for guests. It turns into actively queryable by any AI system that speaks MCP.

Early adopters embody Eventbrite, Shopify, Tripadvisor, O’Reilly Media, Common Sense Media, and Hearst. These are content-rich web sites that already make investments closely in structured knowledge. NLWeb builds immediately on that funding.

Right here’s what this appears like in apply. As an alternative of a consumer navigating Tripadvisor’s search filters to discover family-friendly eating places in Barcelona with outside seating, an AI agent might question Tripadvisor’s NLWeb endpoint: “Discover family-friendly eating places in Barcelona with outside seating and good opinions.” The response comes again as structured Schema.org JSON, prepared for the agent to current to the consumer or act on.

If your enterprise has already invested in Schema.org markup (and Half 2 of this collection defined why you must), you’re nearer to NLWeb readiness than you would possibly assume.

AGENTS.md: Directions For AI Coders

What it is: AGENTS.md is a standardized Markdown file that gives AI coding brokers with project-specific steerage, primarily a README written for machines as an alternative of people.

This protocol is much less immediately related to the entrepreneurs and strategists studying this collection, but it surely’s an necessary piece of the full image, particularly in case your group has improvement groups utilizing AI coding instruments.

AGENTS.md emerged from a collaboration between OpenAI Codex, Google Jules, Cursor, Amp, and Manufacturing facility. The issue they had been fixing: AI coding brokers want to perceive challenge conventions, construct steps, testing necessities, and architectural selections before they’ll contribute helpful code. With out express steerage, brokers make assumptions that lead to inconsistent, buggy output.

Since its launch in August 2025, AGENTS.md has been adopted by over 60,000 open-source projects and is supported by instruments together with GitHub Copilot, Claude Code, Cursor, Gemini CLI, VS Code, and lots of others. It’s now ruled by the Agentic AI Basis, alongside MCP.

The file itself is easy. Plain Markdown, sometimes below 150 traces, protecting construct instructions, architectural overview, coding conventions, and testing necessities. Brokers learn it before making any modifications, getting the identical tribal information that senior engineers carry of their heads.

GitHub reviews that Copilot now generates 46% of code for its customers. When almost half of code is AI-generated, having a normal means to guarantee brokers observe your conventions, safety practices, and architectural patterns isn’t elective. It’s high quality management.

Why this issues for your enterprise: In case your improvement groups use AI coding instruments (and most do), AGENTS.md ensures these instruments produce code that matches your requirements. It reduces agent-generated bugs, cuts onboarding time for AI instruments on new initiatives, and supplies consistency throughout groups.

How They Match Collectively

These 4 protocols aren’t competing. They’re complementary layers in the identical stack.

The stack works like this: MCP supplies the plumbing for brokers to entry instruments and knowledge. A2A allows brokers to coordinate with one another. NLWeb makes web site content material accessible to the complete ecosystem. AGENTS.md ensures AI coding brokers construct appropriately. And the Agentic AI Basis supplies the governance layer, guaranteeing these protocols stay open, vendor-neutral, and interoperable.

The parallel to the authentic internet is not possible to ignore:

• HTTP (transport) maps to MCP (device entry) and A2A (agent communication).
• HTML (content material construction) maps to NLWeb (web site content material for brokers).
• W3C (governance) maps to AAIF (governance).

What’s completely different this time is the pace. HTTP took years to achieve broad adoption. MCP went from launch to common platform help in 12 months. A2A grew from 50 to 150+ companion organizations in three months. NLWeb shipped with main writer adoption at launch. AGENTS.md reached 60,000 initiatives inside its first few months.

The infrastructure is being constructed at web pace, not standards-committee pace. That’s partly as a result of the corporations concerned are the identical ones constructing the brokers that want these protocols. They’re motivated.

And these 4 aren’t the solely protocols rising. Commerce-specific requirements are constructing the transaction layer: Shopify and Google co-developed the Universal Commerce Protocol (UCP), launched in January 2026 with help from Etsy, Goal, Walmart, and Wayfair. OpenAI and Stripe co-developed the Agentic Commerce Protocol (ACP), which powers On the spot Checkout in ChatGPT. CopilotKit’s AG-UI protocol addresses agent-to-frontend communication, with integrations from LangGraph, CrewAI, and Google ADK. We’ll cowl the commerce protocols in depth in Half 5.

What This Means For Your Enterprise

You don’t want to implement all 4 protocols tomorrow. However you want to perceive what’s being constructed, as a result of it shapes what your web site, instruments, and groups needs to be prepared for.

In the event you’ve already invested in Schema.org markup, NLWeb is your closest on-ramp. It builds immediately on the structured knowledge you already keep. As NLWeb adoption grows, your Schema.org funding turns into the basis for making your web site conversationally accessible to AI brokers. Maintain your structured knowledge present and complete.

If in case you have APIs or inside instruments, take into account MCP accessibility. Making your providers obtainable via MCP means any AI platform can work together with them. For ecommerce, that might imply product catalogs, stock programs, and order monitoring turning into accessible to AI procuring assistants throughout ChatGPT, Claude, Gemini, and no matter comes subsequent.

In the event you’re evaluating multi-vendor agent workflows, A2A is the protocol to watch. Enterprise organizations working brokers from a number of distributors (Salesforce, ServiceNow, inside instruments) will more and more want these brokers to coordinate. A2A is the rising normal for that coordination.

In case your improvement groups use AI coding instruments, undertake AGENTS.md now. It’s the easiest protocol to implement (it’s a single Markdown file) and the one with the most fast, tangible profit: fewer bugs, extra constant output, quicker onboarding for AI instruments on your codebase.

The underlying message throughout all 4 protocols is the identical: the agentic internet is being constructed on open requirements, not proprietary ones. The businesses that perceive these requirements early shall be higher positioned as AI brokers grow to be a main means customers work together with companies.

These aren’t stuff you want to implement right this moment. However they are stuff you want to perceive, as a result of Half 4 of this collection will get into the technical specifics of constructing your web site agent-ready.

Key Takeaways

• 4 protocols type the agentic internet’s infrastructure. MCP (instruments), A2A (agent communication), NLWeb (web site content material), and AGENTS.md (code steerage) are complementary layers, not rivals.
• The pace of adoption indicators actual urgency. MCP reached 97 million month-to-month SDK downloads and common platform help in 12 months. A2A grew from 50 to 150+ companion organizations in three months. These are not experiments.
• Opponents are collaborating on infrastructure. OpenAI, Anthropic, Google, and Microsoft are all constructing shared protocols below the Agentic AI Basis. This mirrors the W3C second that unified the early internet.
• NLWeb is doubtlessly the most related protocol for web site homeowners. Constructed by the creator of Schema.org, it turns your present structured knowledge right into a conversational interface for AI brokers. Each NLWeb occasion is robotically an MCP server.
• MCP is the common adapter. Construct one MCP connection to your knowledge, and each main AI platform (Claude, ChatGPT, Gemini, Copilot) can entry it. No extra constructing separate integrations for every platform.
• Begin with what you have got. Schema.org markup readies you for NLWeb. Present APIs can grow to be MCP servers. AGENTS.md is a single file your dev crew can create right this moment. You don’t want to begin from scratch.

The unique internet succeeded as a result of rivals agreed on shared requirements. The agentic internet is following the identical playbook, simply quicker. The protocols are being established now. The governance is in place. The brokers are already utilizing them.

Up subsequent in Half 4: the hands-on technical information for making your web site prepared for autonomous AI brokers, from semantic HTML to accessibility requirements to testing with actual agent instruments.

Extra Assets:

This submit was initially revealed on No Hacks.

Featured Picture: Collagery/Shutterstock