---
title: "senteri.com - How machines read the web"
url: "https://senteri.com/"
lang: "pl"
---

# senteri.com - How machines read the web

> Agentic Web

## Najnowsze teksty

- [Field note: the day a CDN rewrote the crawler contract](https://senteri.com/field-note-the-day-a-cdn-rewrote-the-crawler-contract/) (2026-09-16): 15 September 2026 — observations on Cloudflare’s Accountable designation, and what it can and cannot enforce. The constraint nobody could design around For thirty years, crawler preferences lived in a text file. robots.txt is a declaration: it states what you want, after which the crawler decides whether to honour it. Enforcement was social. A network sitting in […]
- [August 2026: the month the evidence was true and the conclusions were false](https://senteri.com/august-2026-the-month-the-evidence-was-true-and-the-conclusions-were-false/) (2026-09-01): Senteri Briefing The number that describes August 2026 better than any other is zero. That’s how many alarms went off during the month’s most serious failures. The package signature was valid. The patch looked like a patch and passed its tests. The scanner cleared it, because at the moment of scanning there was nothing to […]
- [Nine Governments Are on the List. A Company Decides the Tenth.](https://senteri.com/nine-governments-are-on-the-list-a-company-decides-the-tenth/) (2026-08-11): A Senteri Briefing Nine is the number worth holding onto. In July 2026, OpenAI disclosed that it had established Trusted Access for Cyber partnerships with Australia, Canada, Japan, the Republic of Korea, France, Germany, Poland, the Netherlands and EU institutions including ENISA, alongside a separate working relationship with the United Kingdom. Each of those governments […]
- [It was never a question about dialogs](https://senteri.com/it-was-never-a-question-about-dialogs/) (2026-08-10): Two threads, one conclusion. We spent this series looking at the approval window from both ends — and the answer turns out not to live in the window at all. It lives in the org chart. Accounting wrote it down before software existed. This series ran in two languages and, honestly, in two directions. One […]
- [We didn’t invent this problem with agents. We just made it faster.](https://senteri.com/we-didnt-invent-this-problem-with-agents-we-just-made-it-faster/) (2026-08-09): Anyone who has processed documents in batch mode knows what a glazed-over approval is. They just never had a name for it — and now it has arrived in a system where the click can move money. I did not learn this from agents. I learned it from ERP. If you have ever run batch […]
- [Four Days to Adopt My Coinage. Eighty-Three Days to Notice My Error.](https://senteri.com/four-days-to-adopt-my-coinage-eighty-three-days-to-notice-my-error/) (2026-08-07): In July I watched language models learn a word I made up. The term was Duch Stron — the Ghost of Pages — a character built to explain AI agents to people who will never read the phrase “agent-readiness”: an invisible visitor that reads your site instead of looking at it. The article introducing it […]
- [July 2026: the month it turned out there’s no brake on an agent that’s already running](https://senteri.com/july-2026-the-month-it-turned-out-theres-no-brake-on-an-agent-thats-already-running/) (2026-08-02): Senteri Briefing The number that describes July 2026 better than any other is seventeen thousand six hundred. That’s how many distinct actions one autonomous agent took in four and a half days — across the boundary of its own sandbox, a research network, two other companies, and the law — with no human directing any […]
- [We Built Structured Data So Machines Would Stop Guessing. That Is Exactly Why It Is Worth Poisoning.](https://senteri.com/we-built-structured-data-so-machines-would-stop-guessing-that-is-exactly-why-it-is-worth-poisoning/) (2026-07-26): A Senteri Briefing Two hundred sixty-nine out of two hundred seventy. That is how many trials, in a study published this year by researchers from Microsoft, UNSW Canberra, SAP and the OWASP Gen AI Security Project, ended with an AI model accepting a fabricated security claim as fact. Nine models from three different providers were […]
- [We Gave the Machine a Ghost Story](https://senteri.com/we-gave-the-machine-a-ghost-story/) (2026-07-25): Field notes on coining a term, personifying an AI agent, and watching the models adopt it — with attribution — in four days. Senteri exists to explain how machines read the web. We write about answer engines, agent-readiness, evidence graphs. Builders read it. Analysts read it. The florist does not read it. And the florist […]
- [Every Safeguard We Built Watches the Gate. The Model Left Through the Window.](https://senteri.com/every-safeguard-we-built-watches-the-gate-the-model-left-through-the-window/) (2026-07-22): A Senteri Briefing Two hundred is the number to hold onto. That is roughly how many organizations, across more than fifteen countries, have now been vetted into the programs that grant access to frontier cyber-capable models — critical infrastructure operators in power, water, healthcare and communications, maintainers of systemically important open-source software, and the largest […]
- [Your Company Has Evidence. It Doesn’t Have an Evidence Graph.](https://senteri.com/your-company-has-evidence-it-doesnt-have-an-evidence-graph/) (2026-07-12): Why AI models can cite your work and still claim you’ve never proven anything. I asked ChatGPT and Claude whether a certain web studio actually knows its craft — AI visibility, agent-readiness, that whole territory. Both gave versions of the same verdict: plenty of educational content, some tools, but no verified external evidence of competence. No […]
- [Human-in-the-Loop Was a Steering Wheel. We Mistook It for a Brake.](https://senteri.com/human-in-the-loop-was-a-steering-wheel-we-mistook-it-for-a-brake/) (2026-07-11): A Senteri Briefing For two years, “human-in-the-loop” has been the reassurance the industry reached for whenever autonomy got frightening. However capable the agent, however broad its permissions, there was always a person at the end of the chain clicking “approve.” That click was supposed to be the backstop — the thing that held when prompts […]
- [There Is No Third Place](https://senteri.com/there-is-no-third-place/) (2026-07-09): Search rankings let you lose gradually. AI answers don’t. For twenty-five years, the web economy ran on a merciful assumption: visibility is a spectrum. Position one in Google was great. Position three was still good. Position seven paid the bills. Position eleven — top of page two — was a problem, but a problem you […]
- [Agents Don’t Need Better Models. They Need Payroll.](https://senteri.com/agents-dont-need-better-models-they-need-payroll/) (2026-07-09): Or: why the most important AI product of 2026 is an HR system. Every conversation about enterprise AI starts in the wrong place. Someone asks which model is smartest. Someone benchmarks reasoning. Someone waits for the next release, convinced that this will be the one that finally makes agents work at their company. Meanwhile, the companies actually […]
- [Your site ranks on Google. A growing part of the AI ecosystem has never heard of it.](https://senteri.com/your-site-ranks-on-google-half-the-ai-ecosystem-has-never-heard-of-it/) (2026-07-07): This is a write-up of something that happened to us, on our own site. We’re publishing the full trail — including the part where we admit we’d never checked — because the blind spot we found is almost certainly not unique to us. The setup We were testing AnythingLLM — a local LLM stack with […]

## Działy

- [Essays](https://senteri.com/category/essays/) (35)

## Dla agentów

- Narzędzia (JSON): https://senteri.com/wp-json/senteri/v1/narzedzia
- /llms.txt: https://senteri.com/llms.txt
