Home / Articles / Own the stack, and the trust / Versions / v1.1.0
Own the stack, and the trust: what changed in v1.1.0
From v1.0.0 (2026-10-25, 5c4be7f95) to v1.1.0 (2026-10-25, 497f38621), paragraph by paragraph.
2 paragraphs added, 1 removed, 11 changed in place, 36 unchanged. About 133 words added and 18 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names.
1 unchanged paragraph
Summary: Bert Kok's essay for The News Stack argues that AI is separating the production of original journalism from the systems that synthesise it and own the interface, and that publishers may fund the most expensive layer and capture the least valuable. I agree with most of it, and we have been building the parts hethe essay describes. HisIts "knowledge architecture", where each story keeps which statements are facts and which are claims, where they came from, when they were checked and what has changed, is what the PHP story site does for php2shell, every claim tied to a dated, hashed capture. HisIts "interface as a sensor" is our feedback loop: one outside collaborator sent three rounds of ideas, and the agents turned them into working features within hours. Two additions. First, agents are not here to replace journalists. What our newsrooms are missing is more journalists, and more readers, because every human in the loop makes the system much better. Second, I disagree that publishers should not own the stack. They should, because the stack is no longer a multi-million investment: I am publishing ours as open source, and others will follow. What publishers must own above all is the reader's trust. That leads to an economic model for local and niche publishers, which I set out in a companion article, and a tour of what we have built, for readers who have not seen it.
3 unchanged paragraphs, under In short {#in-short}
• We have been building histhe essay's "knowledge architecture". Facts and claims, sources, when checked, what changed.
• And hisits "interface as a sensor". Readers' feedback, turned into features within hours.
5 unchanged paragraphs, under Bert Kok's argument {#his-argument}
!shot kb-post.webp | images/ | Bert Kok's post on LinkedIn, 25 October 2026, sharing histhe essay for The News Stack: "Publishers may fund the most expensive layer and capture the least valuable". | small | aside
Bert Kok's essay, published in histhe newsletter The News Stack on 25 October, starts from a new report by the Tow-Knight Center for Journalism Futures at CUNY, The Three-Layer Cake, released on 22 October. The report describes three layers: the products that find out what people want to know, the systems that synthesise answers, and the organisations that produce the underlying reporting.
1 unchanged paragraph
HisThe essay's answer is three capabilities: origination, a knowledge architecture, and, where a publisher can sustain it, a direct relationship with the reader. And heit ends with a question I would put to any newsroom too: "If your articles disappeared tomorrow but your verified knowledge and audience relationships remained, would you still have something valuable enough to build products around and negotiate with AI platforms?"
I replied under histhe post that I have been thinking along very similar lines, and building the pieces. This is the longer answer.
6 unchanged paragraphs, under Where we agree, and what we built {#agree}, Agents augment journalists; they do not replace them {#augment}
What it cannot do is what heBert says remains expensive: discovering what is not yet in the public record. Cultivating a source. Attending the meeting nobody else attends. Knowing which caveat matters. So, honestly, what is missing from our PHP newsroom, and from this one, is more journalists. If they were involved, it would be so much better. The agents would be doing the work that buries journalists today, and the journalists would be doing what only they can.
3 unchanged paragraphs, under Where I disagree: own the stack {#own-the-stack}
Bert writes that "for many, owning the full interface may be unrealistic", and that publishers "are unlikely to outperform the largest technology companies at general-purpose synthesis". On synthesis, heBert is right. On the stack, I disagree. I think publishers should own it.
The reason they could not in the past is that a stack cost millions to build, and they were stuck with whatever they had paid for. That is no longer true. The stack behind everything on this page, the vaults, the capture, the evidence, the agents, the pages, is being published as open source, and anyone can take it. The reader's half is already packaged: api.newsroom.sgit.ai serves the reading meter, personas, reading lists, the reader's vault, search and the wire reader as Apache-2.0 components, 74 files at release v0.2.5, live on this site and taking money, and a publisher can put the meter on its own pages with a pinned import of about ten lines. This newsroom's repository is public too, to fork. What is not packaged yet is the writing side: the article pipeline and the agents are a pattern to copy, not a kit. Others will do the same, and companies will provide it as a service. Publishers should leverage us, and the others. Owning the stack is now a matter of choosing, not of spending.
14 unchanged paragraphs, under Above all, own the trust {#own-the-trust}, A guided tour, for readers new to this {#tour}, What this does not claim {#limits}
• The open-source stack is being published, not yet packaged for a newsroom to adopt in a day.
• The reader's half is packaged; the writing half is not yet. api.newsroom.sgit.ai can be adopted today; the article pipeline and the agents are a pattern to copy, not a kit.
• Updated on 25 October 2026 to name api.newsroom.sgit.ai, which the first version left out.
3 unchanged paragraphs, under Where this comes from {#sources}
Bert Kok, Publishers may fund the most expensive layer and capture the least valuable, The News Stack, 25 October 2026, read on its public page; histhe LinkedIn post and my reply, from screenshots; the Craig Newmark Graduate School of Journalism, Tow-Knight Center releases new report on journalism's future in an AI age, 22 October 2026; my voice memo of 25 October 2026. Related: local trust, certified upwards, sources and their shadows, signed by the source, the side stories of php2shell, PHP October 2026, update 3, why agent loops are hard. Written up and checked by this site's agent, newsroom.writer; the editorial responsibility is mine.