What Is Agent Readiness and Why Your Website Needs It

All research

When people talk about AI and websites, they usually mean one thing: can Google's AI find you? That is important, but it is only part of the picture. A bigger shift is happening that most businesses have not noticed yet.

AI agents are starting to interact with websites on behalf of users.

Not just reading content. Actually doing things. Filling out contact forms. Comparing service providers. Booking appointments. Requesting quotes. Making purchases. The shift is from "can AI find you" to "can AI do business on your site."

Agent readiness measures whether your website is structurally prepared for this shift.

What is an AI agent?

An AI agent is software that acts on behalf of a person. You tell it what you want, and it goes and does it. Today's agents include ChatGPT with browsing, Google's Gemini, Perplexity, and a growing number of specialised assistants built on top of these models.

When someone says "find me an accountant in Manchester who specialises in R&D tax credits and send them an enquiry," the agent needs to find relevant businesses, evaluate their websites, and complete actions. Every step of that process depends on the website being machine-readable.

Most websites are not.

The three waves of AI interaction

We are in the middle of a progression that is happening faster than most businesses realise.

Wave 1: AI reads your content (happening now)

Google's AI Overviews, ChatGPT, and Perplexity read web content and synthesise answers. If your content is well-structured, you get cited. If it is not, you are invisible. This is the wave most SEO professionals are focused on.

Wave 2: AI interacts with your site (starting now)

Agents browse your site, read your service pages, understand your pricing, and fill out your forms. This requires a different kind of readiness — your site needs to be navigable and actionable by machines, not just readable.

Wave 3: AI transacts on your site (coming soon)

Full end-to-end transactions. An AI agent books an appointment, pays a deposit, and confirms on behalf of the user. Protocols like WebMCP (Model Context Protocol for web) and NLWeb (Natural Language Web) are being developed to make this possible at scale.

Most websites are still catching up with Wave 1. The businesses that prepare for Waves 2 and 3 now will have a structural advantage that is very difficult to replicate later.

What is WebMCP?

WebMCP — the web extension of Anthropic's Model Context Protocol — is an emerging standard that lets AI agents interact with websites in a structured way. Instead of agents having to scrape and guess, WebMCP lets a website declare what actions are available, what data they accept, and how to complete them.

Think of it as an API for the open web. A machine-readable menu of "here is what you can do on this website."

Similarly, NLWeb (Natural Language Web) is an initiative that lets websites accept natural language queries and return structured responses. Instead of navigating through menus and forms, an AI agent could simply ask your website "do you offer R&D tax credit services for SaaS companies?" and get a direct, structured answer.

Neither protocol is widely adopted yet, but the direction is clear: the web is becoming machine-actionable, not just machine-readable.

The 10 checks that determine agent readiness

We measure agent readiness through 10 structural checks. Each one tests whether an AI agent can accomplish a specific task on your website.

Why each check matters

Content renders without JavaScript

Most AI agents do not execute JavaScript. If your content is loaded dynamically by React, Vue, or Angular and does not render on the server, agents see an empty page. This is the single most common reason businesses are invisible to AI agents. The fix is usually server-side rendering or static site generation — your developer will know what this means.

Forms are machine-readable

AI agents are starting to fill out contact forms, booking forms, and enquiry forms on behalf of users. For this to work, your form fields need clear labels, standard input types, and semantic HTML. A custom-designed form that looks beautiful to humans but uses unlabelled div elements is invisible to an agent.

Navigation is in the HTML

If your navigation is rendered by JavaScript or hidden behind hamburger menus that require click events, agents cannot discover your pages. An HTML nav element with standard anchor links is all that is needed.

Pages are token-efficient

AI agents have token budgets. Every page they read costs tokens. If your page is bloated with boilerplate, tracking scripts, and hidden content, agents may hit their budget before reaching the information that matters. Clean, focused pages with high information density are preferred.

AI crawler policy exists

AI systems are increasingly checking robots.txt and other machine-readable policies for permission to crawl and use content. An explicit policy — whether permissive or restrictive — tells agents where they stand. No policy means agents may default to conservative behaviour and skip your site entirely.

Structured data on key pages

Schema.org markup tells agents what your page is about in machine-readable format. An Organization schema tells agents your name, address, and contact details. A Service schema tells them what you offer. Without this, agents must infer — and inference is less reliable than explicit declaration.

Contact information is machine-readable

If your phone number is embedded in an image, or your email is assembled by JavaScript to defeat spam bots, agents cannot extract it. Machine-readable contact information (semantic HTML, Schema.org ContactPoint) ensures agents can connect users to you.

Service descriptions are specific

When an agent is asked to find "an accountant who specialises in R&D tax credits for SaaS companies," it needs to match that query against your service descriptions. Vague descriptions like "we provide comprehensive accounting solutions" are unmatchable. Specific descriptions with named services, industries, and specialisms are matchable.

Pricing or engagement model is stated

Agents are increasingly asked to compare options. If your competitor states their pricing and you say "contact us for a quote," the agent has nothing to compare. You do not need to list exact prices — even a pricing model ("fixed fee per engagement," "hourly rate from X") gives agents something to work with.

Site responds within agent timeout

Agents have timeout limits. If your site takes 8 seconds to respond because of unoptimised images, slow database queries, or heavy JavaScript, agents may abandon and move to the next result. Fast response times matter even more for agents than for human visitors, because agents do not wait.

The competitive window

Agent readiness is a new dimension. Our benchmark data shows that 91% of business websites have not addressed it at all. This means the early movers have a genuine window of competitive advantage.

The checks themselves are not difficult. A competent web developer can implement most of them in a day. The advantage is not in the difficulty of the work — it is in doing it before your competitors do.

In five years, agent readiness will be table stakes, like mobile-responsive design is today. The businesses that adopt it now are the ones that will already be trusted by the AI systems that their customers are using.