Why I built Open for Agents

I have been a web publisher and webmaster for more than 20 years. That is long enough to see a few big changes in how people use the internet.

We went from directories to search, from desktop to mobile, and from typing in an address to finding almost everything through a platform. I think the next change is already taking shape.

People will still visit websites, but they will do less of the routine browsing themselves. We will have personal assistants that can go out, find information, compare options, check what has changed, and carry out useful tasks for us. Those assistants will have to deal with websites every day.

AI is here to stay. Agents are coming with it.

Machines are already using our websites

As a publisher, I can already see how much website traffic is not a person sitting down to read a page.

Some of it is familiar search crawling. Some of it appears to be bots, automated systems, and AI-related crawlers. I cannot always tell whether a particular request is collecting search data, training a model, looking for an answer, or simply probing the site.

What I can see is the behaviour. Automated traffic follows broken links, requests hundreds of variations of the same page, repeatedly lands on 404s, and consumes hosting and infrastructure without behaving anything like a human visitor.

Blocking every machine is not a realistic answer. Letting every machine guess its way around the site is not a good answer either.

The missing interface

Most websites were built for people. The meaning of the site is spread across page copy, menus, forms, buttons, and visual layouts. A machine has to crawl all of that and infer what matters.

When I saw WebMCP, the direction made sense to me. A website can provide explicit tools with defined inputs and structured results. An agent does not have to pretend to be a person clicking around a page when the site can tell it, clearly, what is available.

But a protocol alone does not answer the question I care about as a website owner:

What should an agent be allowed to know and do on my site?

That is the reason I built Open for Agents.

It gives the owner a place to discover possible capabilities, review them, decide what is appropriate, publish only the approved surface, and check what an agent can actually see. It is not about handing the website over to AI. It is about creating guardrails before agents become a normal part of using the web.

WordPress is the flagship because it is the platform I know from years of real publishing work, including the unglamorous details that decide whether something actually works: plugins, caching, redirects, forms, shops, and public hosting.

Different products for different jobs

The same need appears in different forms, so Open for Agents now covers three related products:

• Open for Agents for WordPress governs the site knowledge and capabilities an owner chooses to publish.
• Open for Agents for Shopify is a separate, public, read-only app that checks whether supported AI shopping catalogue evidence still agrees with the merchant's store.
• Any-Web is a controlled preview of a grounded, cited conversation over reviewed public material.

The optional Open for Agents Assistant adds a conversation to a WordPress site. It uses the owner's reviewed capabilities, shows consequential actions before they happen, and keeps checkout, payment, and sensitive account work with the visitor.

What I am trying to prove

I am not trying to make every website autonomous, and I am not building against agents. I am building for a web where agents are normal.

Agents can be genuinely useful. They can also create more crawling, more guessing, more cost, and more risk if website owners are left without a proper interface or any meaningful control.

I want publishers, merchants, and site owners to have a practical say in how this next version of the web works. The website should remain authoritative. The owner should choose the capabilities. The agent should work through a reviewed surface instead of inventing one from whatever it can scrape.

If you run WordPress, the best place to begin is the current Core plugin on WordPress.org. If you want to see the idea working first, try the live Storefront Assistant.