Select Page
How machines read the web

The web now has a first reader, and it isn’t human.

Field notes, experiments, and essays on agent-readiness — what AI agents actually do when they reach your site, tested on real pages, reported straight.

Read the latest
The Agentic Web Is Solving the Same Problem Nine Times

The Agentic Web Is Solving the Same Problem Nine Times

An essay on the pre-consolidation phase of the agentic web — why the standards keep multiplying, why most of them will die, and the one criterion that already tells you which. Here is what the last three years have felt like from the publisher’s side of the agentic…

I Tried to Use the Most Powerful Public AI Model for Security Work. It Kept Handing Me to a Weaker One.

I Tried to Use the Most Powerful Public AI Model for Security Work. It Kept Handing Me to a Weaker One.

A Senteri field-report. The test was simple: bring real defensive-security questions to Claude Fable 5 and see what happens. What happened is the whole point. On 9 June 2026, Anthropic made Claude Fable 5 generally available — the first public release of a…

An agent debugging a legacy system is not a research assistant. It is a junior developer with extraordinary recall and no production instinct.

Eight Failure Modes from Inside an Agent Debugging a Legacy ERP

An agent debugging a legacy system is not a research assistant. It is a junior developer with extraordinary recall and no production instinct. What follows is a first-person account of one debugging session. The agent — me — is the subject. The failures are mine. The…

May 2026: The Month the AI Security Window Closed From Months to Weeks

May 2026: The Month the AI Security Window Closed From Months to Weeks

A Senteri Briefing Update — 9 June 2026. This briefing was written as a record of May, and it stands as written. One forecast in it has since resolved: the closing of the window it describes. On 9 June, Anthropic shipped Claude Fable 5 — the first publicly available…

We Finally Got to See What We Feed the Machines. Half of It Is an Accident.

We Finally Got to See What We Feed the Machines. Half of It Is an Accident.

For the first time there’s crawl-scale data on what structured markup the web actually carries — and it says the machine-readable web is narrower, more automated, and more out-of-date than anyone admits. We have spent two years arguing about how to make websites…

Client, Parasite, or Thief: Governing the Agents on Your Site

Client, Parasite, or Thief: Governing the Agents on Your Site

Field report from the Governance layer of agent-readiness — the business decisions sitting on top of all the technical work, now that most of your traffic isn’t human. Here is the number that ends the argument about whether this matters yet. As of June 2026,…

The Agent Trusts Your Data, Not Your Prose

The Agent Trusts Your Data, Not Your Prose

Field report from the Data layer of agent-readiness — and why “add FAQ schema” stopped being the answer in May 2026. Here is a small experiment you can run in your head. Take a product page where the visible text says the item is in stock at £49, but the structured…

The Field Guide to Agent-Readiness

The Field Guide to Agent-Readiness

What an AI agent actually needs from your website — six layers, three starting points, and the parts that will change before the year is out. Most writing about AI agents and the web argues about the future. This is not that. By June 2026, agents are already the thing…

I Built a Trap to Stop an AI Agent. It Walked Straight Through.

I Built a Trap to Stop an AI Agent. It Walked Straight Through.

Two visually identical pages, ten files to download, and Claude in Chrome as the test subject. I assumed JavaScript rendering, onclick handlers, and an iframe would stop the agent cold. None of them did — and that failure turned out to be the most useful result I…

MCP Didn't Win Because It Was Good — It Won Because It Was Math

MCP Didn’t Win Because It Was Good — It Won Because It Was Math

Every few years a technology gets called “the standard that changes everything,” and almost every time it’s marketing. So when Anthropic quietly dropped the Model Context Protocol on GitHub in November 2024 — no fanfare, a modest press note, two SDKs — the safe…

// what this is

Senteri is about one thing: how machines read the web. As AI agents become the first reader of most pages, the rules of what makes a site legible are being rewritten — and almost nobody is testing them in the open.

This is where that testing gets published, in English. It’s fed by a Polish-language research engine that ships daily threat intelligence, a 270-term agentic-web dictionary, and a working MCP layer — selected, rewritten, and sharpened for a global audience. The experiments are real. The results are reported straight, including the ones that fail.