The Agentic Web Is Splitting into Two Bets: Identity and Capability

The protocol layer of the agentic web is splitting into two bets, and most websites have already placed one of them without knowing it. The first bet is about identity: a file called llms.txt that tells AI models who you are and what your content covers.

The second is about capability: a browser standard called WebMCP that tells an agent what it can actually do on your website once it arrives. They sound like the same idea.

2 Files, 2 Questions

An agent that lands on your website has two things it might want to know. The first is what this place is and what it covers. The second is, now that it is here, how it completes the task its user sent it to do. Identity, then capability. The strategic issue is whether automated visitors can understand, trust, and complete the same journey a human visitor can. Agent readiness is partly technical, but it is also about clear tasks, accessible flows, and reliable evidence.

The risk is usually hidden in the execution layer. A page can look fine to a human and still fail for an automated visitor if the form, call to action, rendering path, or confirmation step is not accessible enough for the agent to complete the task. The same pattern also shows up in 4 Layer AI Ops Playbook, where the practical question is how the signal becomes visible.

The Identity Bet: LLMs.txt

Llms.txt is a markdown file that lives at yourdomain.com/llms.txt. It was proposed by Jeremy Howard, co founder of Answer.AI, on September 3, 2024, as a way to hand language models a clean, human curated index of your content instead of. For search teams, the important part is not the headline movement by itself. It is whether the shift changes which communities, forums, video surfaces, or publisher pages now satisfy the query better than the old ranking pattern.

The reporting question is whether this signal changes a decision. If it only creates another number in a dashboard, it adds noise. If it helps separate profile activity, website visits, calls, bookings, and direction requests, it can make local performance easier to understand.

The Capability Bet: WebMCP

WebMCP, short for Web Model Context Protocol, is a browser standard that lets your website register callable tools an agent can invoke through a navigator.modelContext API. It starts from a different question than the identity file: not. The strategic issue is whether automated visitors can understand, trust, and complete the same journey a human visitor can. Agent readiness is partly technical, but it is also about clear tasks, accessible flows, and reliable evidence.

Why The Two Bets Are Not Interchangeable

The cleanest way to hold the difference is through the two design constraints I keep coming back to in Machine First Architecture: identity and interaction. Identity is making your brand and your content unambiguously machine readable. The practical read is that brand signals need to be consistent enough for both people and AI systems to form a stable view of the company, its expertise, and its trust signals.

I Placed Both Bets On My Own Website, Deliberately

I run both on No Hacks, and the contrast between how much each one costs to place is the whole argument in miniature. For identity, I keep an llms.txt, and I generate it from the website's own content each time I update the site, rather. The strategic issue is whether automated visitors can understand, trust, and complete the same journey a human visitor can. Agent readiness is partly technical, but it is also about clear tasks, accessible flows, and reliable evidence.

What This Means For Your Website

First, find out what you have already published. Open yourdomain.com/llms.txt in a browser. If something loads, your stack put it there, possibly a plugin default you never set. Read it. Ask whether it actually describes your website,. The strategic issue is whether automated visitors can understand, trust, and complete the same journey a human visitor can. Agent readiness is partly technical, but it is also about clear tasks, accessible flows, and reliable evidence. This connects with Make Something Agents Want when the same signal needs a clearer operating decision.

What Is Still Unsettled

The honest uncertainty: The identity bet is not dead; it is unproven. If a major AI system announces tomorrow that it reads llms.txt and weights it, the calculus shifts, and the file everyone defaulted into suddenly earns its place. I am. The strategic issue is whether automated visitors can understand, trust, and complete the same journey a human visitor can. Agent readiness is partly technical, but it is also about clear tasks, accessible flows, and reliable evidence.

2 Files, 2 Questions in practice

Introduction The protocol layer of the agentic web is splitting into two bets, and most websites have already placed one of them without knowing it. The first bet is about identity: a file called llms.txt that tells AI models who you are. For search teams, the important part is not the headline movement by itself. It is whether the shift changes which communities, forums, video surfaces, or publisher pages now satisfy the query better than the old ranking pattern.

What the visibility signal actually changes

What the visibility signal actually changes: the Agentic Web Is Splitting into Two Bets: Identity and Capability: the Practical Angle should be treated as a visibility signal, not a standalone headline. Introduction The protocol layer of the agentic web is splitting into two bets, and most websites have already placed one of them without knowing it. The first bet is about identity: a file called llms.txt that tells AI models who you are and what your content. A useful companion note is Two Ways Brands Appear in AI Search, because it looks at a nearby part of the same system.

What the visibility signal actually changes: the practical question is whether the page, brand evidence, and surrounding content make the answer easier to trust. If that support is weak, search systems can still understand the topic but fail to connect it confidently to the brand.

What the visibility signal actually changes: that is why the response should begin with an audit of the evidence already on the site before creating a new asset. The fastest improvement is often a clearer page, a better internal link, or a stronger explanation of why the brand belongs in the answer.

Where the evidence needs to be tested

Where the evidence needs to be tested: a single study or ranking observation should not become a strategy by itself. It should become a diagnostic prompt: which source is being trusted, which query pattern is affected, and which part of the site would make that trust easier to earn?

Where the evidence needs to be tested: that keeps the response grounded. The goal is to improve the evidence chain around the topic rather than publish another summary that repeats what every other page already says.

Where the evidence needs to be tested: the important distinction is between a useful signal and a fashionable talking point. A useful signal changes the brief, the page structure, the linking plan, or the measurement view.

How to avoid overreacting to one data point

How to avoid overreacting to one data point: for content teams, the strongest move is to map the claim to existing assets before creating anything new. The right page may already exist, but it may need clearer headings, stronger internal links, fresher proof, or a better explanation of why the brand belongs in the answer.

How to avoid overreacting to one data point: this is also where title rewriting matters. A title should not copy the source headline; it should frame the practical implication so readers immediately know why the topic deserves attention.

How to avoid overreacting to one data point: the same standard should apply to every section. Each heading needs to earn its place by moving the reader through the evidence, not by repeating the outline in a more polished voice.