The route
From request to published page
Hover any station to open its detail card. Move the cursor away and it collapses. Keyboard: Tab to a station, Esc to close. On touch, tap to open.
The task
Step 01 · Generator
Brief
A request like “we need something about X” becomes an editorial task. The brief records:
- who the content is for;
- which reader problem it solves;
- what the reader should learn or gain;
- why the business needs it;
- which metric will show if it worked.
Working hypotheses are recorded separately. These are assumptions that sound plausible but have not yet been proven.
What is usedA model for complex reasoning · a brief template · version history in Git
Step 02 · Generator
Checking what is already published
The team checks what the company has already published on this topic: which search queries overlap, which terms are already defined, and whether any pages contradict each other. After this check, one of three decisions follows:
- create a new piece of content;
- add to an existing one;
- merge several pages.
Without this check, the website fills up with duplicate articles, different definitions of the same term, and advice that contradicts itself. That makes it harder for search engines and AI assistants to identify which version is current and reliable.
What is usedVector search · a list of published pages · a glossary of terms and entities
Checkpoint 1 of 4 · Editor
Is the idea approved?
Checkpoint 1 · Human
Is the idea approved?
The editor looks at the audience, the purpose of the content and the expected result. An approved topic does not yet mean that every future claim can be proved.
The decision is recorded together with the name of the responsible person, the date and any approved exceptions.
RoutingYes → step 03 · No → step 01 · Topic rejected → archive, with the reason written down
Evidence
Step 03 · Generator
Collecting evidence
The work has four parts:
- finding and downloading sources;
- splitting the content into separate claims that can be checked;
- checking that all required fields are filled in;
- sending difficult claims to an expert.
Every claim gets a unique ID, an exact quote, a date and a defined scope. A study result for one market, for example, cannot be applied to every country without extra evidence.
The team also records where the information came from. A full page and its short description in search results are not the same thing: a search snippet helps you find the right source, but it cannot confirm facts, numbers or exact wording.
You can use a faster, lower-cost model to find sources. But it is better to use a stronger model to read them and turn them into separate claims.
What is usedA lower-cost model for search · a stronger model for reading sources · an automated browser · a PDF parser · saved copies of sources with hashes
If no evidence is found — the work goes back.
Step 04 · Checker
Independent verification
The checker downloads every source itself and checks three things:
- the quote is present in the source;
- it supports exactly the claim that was written down;
- the claim does not go beyond its stated scope.
It also looks for broken links, unsupported generalisations and mistakes in attribution — for example, when the words of one person or company are given to another.
If the checker cannot download pages, it can only judge whether the reasoning is consistent. In that mode it cannot confirm that the source contains the fact: the link may be real, but the required number may not be on the page.
What is usedA model from a different provider · a required second download of the source · a verification result stored in the metadata
If a source was misinterpreted, the work goes back.
Checkpoint 2 of 4 · Code
Has the evidence passed the check?
Checkpoint 2 · Code
Has the evidence passed the check?
The orchestrator — the program that starts the steps and passes the work between them — reads the status of the check from the metadata. If the evidence is blocked, the next step simply does not start.
This is what separates a process from a set of prompts. Here the status BLOCKED is not a comment for the next agent. It is an enforced stop command.
RoutingPASS → step 05 · No source → step 03 · An expert is needed → the expert’s answer is recorded as a source, then step 03
Content design
Step 05 · Generator
Collecting data about search and AI answers
Once the evidence is collected and checked, the system defines the information need that the future content must meet. It looks at several things at once:
- real questions from users;
- keywords and search queries;
- traditional search results;
- answers from popular AI assistants;
- pages that AI uses most often as sources;
- how easy it is to find and extract information from the brand’s own website;
- key concepts, companies, products and terms linked to the topic.
Based on this data, the team decides the main search query, secondary queries and related topics, the user questions that must get an answer, and the sections needed to cover the topic fully.
The result is a map of information gaps — a list of questions that existing content answers poorly: incompletely, inaccurately, in contradictory ways, or not at all.
What is usedA search results API · test queries sent to AI assistants · on-site search history · user support requests · vector clustering of queries and documents · a model that analyses and groups the results
Step 06 · Generator
Content specification
The core of the specification is a matrix:
section → claim IDs → sources → check status
A section can enter the structure only if it has claims that passed the check.
For every section, the team writes one key takeaway — the single idea the reader should remember. The system then checks whether the chosen claims really support it.
Search demand shows which questions are worth covering. The evidence defines what each section can claim.
What is usedA model for complex reasoning · the claim register · data about search and AI answers · the list of published pages
Checkpoint 3 of 4 · Editor & expert
Is the structure approved?
Checkpoint 3 · Human
Is the structure approved?
The editor and the expert approve the whole evidence matrix, not just a list of headings.
If a section has no confirmed claims, it goes back to research or is deleted. The expert’s answer is also recorded as a source, with a name, a date and a defined scope. Otherwise, the fact-check will treat it as unconfirmed.
RoutingYes → step 07 · No → step 05
Production
Step 07 · Generator
Draft
The model writes the text using only the approved claim register. It is free to choose the structure, the rhythm and the wording, but it cannot change or add facts.
The draft exists in two layers:
- clean text for the reader;
- a working version where every factual sentence is linked to a claim ID.
Thanks to the second layer, the checker does not have to guess which source a sentence is based on.
What is usedA model tuned for prose · a tone of voice guide with no factual information in it · the claim register
Step 08 · Checker
Fact-checking and conclusion checks
This step has two separate checks.
- Fact-check: every factual sentence is matched to a specific claim by its ID.
- Conclusion check: the system decides whether the conclusion of a section really follows from the sources provided.
The second check finds a particularly dangerous type of mistake: every quote is correct on its own, but the cause-and-effect story built from them is not supported by any source.
What is usedA model from a different provider than the model used at step 07 · matching by ID · an error classifier
Getting ready to publish
Step 09 · Generator
Preparing the text for search and citation
The goal of this step is to help a reader, a search engine or an AI assistant find and quote the right answer quickly. The content is updated to include:
- a direct answer at the beginning;
- self-contained sections that make sense on their own;
- tables with consistent column types;
- an FAQ section;
- metadata;
- internal links to pages that exist.
After this work, the set of claim IDs must stay the same. If a new fact appears, the content goes back to the earlier steps.
What is usedA mid-tier language model · an up-to-date list of website pages
Step 10 · Generator
Editing for clarity and style
The editor removes empty generalisations, promotional language and stock phrases common in AI-generated text. For every such phrase, they check whether there is a proven fact behind it:
- if there is a fact, the vague wording is replaced with a specific one;
- if there is no fact, the phrase is deleted.
You cannot take a suitable fact from another part of the register just because it sounds convincing. This can change the meaning or scope of the claim.
After this kind of editing, the text often becomes 15–30% shorter.
What is usedA language model · an editorial guide · a scanner for signs of machine-written text · automatic checks of numbers, dates, negative wording and attribution
Step 11 · Checker
Legal and product risks
Whether the text sounds like the company, and whether the company has the right to say such things, are two different questions. This is why style and risk are checked separately, with different people responsible for each.
Claims about the company are compared with the approved fact sheet. Wording about promised results, licences, competitor comparisons and other risks is checked against the compliance rules.
If there are no such rules, the process stops. The model must not replace company or legal requirements with its own “careful” wording.
What is usedA separate checker model · the company fact sheet · the compliance rules
Step 12 · Checker
Final check of meaning
The content is checked for meaning, not by comparing every character:
- all the claims are still there;
- the scope of each claim has not expanded;
- limitations and attribution have not been lost;
- the conclusions still follow from the sources;
- the required sections from the specification are present;
- no new facts have appeared.
This check is needed because the text goes through several more rounds of editing after the fact-check. Without it, the version that was checked and the version that is published can be noticeably different.
The checker reviews the text from the start without seeing the results of earlier checks.
What is usedAn independent checker · a separate checking script · automatic checks of the required conditions
Step 13 · Code
Technical checks and version freeze
Code, with no model involved, checks:
- whether external links open;
- whether internal pages exist;
- whether the markup matches the visible text;
- whether the metadata is filled in;
- whether any internal notes remain in the content;
- whether the preview looks correct;
- whether a rollback point has been created.
After the check, the version is frozen. Any later changes require a new check.
What is usedA link checker · a markup validator · a preview renderer · creation of a hash and a rollback point
Checkpoint 4 of 4 · Person responsible for publishing
Do we publish this version?
Checkpoint 4 · Human
Do we publish this version?
The person responsible for publishing approves the document. The log records their name, the time, the version of the package and any accepted exceptions.
RoutingYes → step 14 · No → back to the previous step · Publication refused → archive, with the reason written down
Step 14 · Code
Publishing and checking the live page
After approval, the content goes to the content management system and is published with no extra changes. No generative models are used at this step, which ensures that the published version is exactly the version that passed all the checks.
After publishing, the system automatically opens the live page and compares it with the approved version of the document. This confirms that nothing changed during publishing: no blocks of text disappeared, the markup did not break, and no formatting errors appeared.
What is usedThe CMS API · a second download of the published page · the saved approved version of the document · a rollback mechanism
Life cycle
Step 15 · Code
Monitoring and updating
The work does not end when the content is published. The system tracks:
- the metric defined in the brief;
- whether the content appears in answers from AI assistants;
- whether sources are still available and whether they changed;
- how long each product fact remains valid;
- the date of the next review;
- who is responsible for updates.
All links are downloaded again on a regular basis. If a source has disappeared, changed, or stopped supporting the claim, the system creates a task to check it.
What is usedA scheduler · repeated downloading of links · measurements of how often the page is cited · logs of visits by AI bots
Parallel branch · separate output
Content for social media
A post is not just a shorter article. It has a new hook, a different context and shorter wording. During this kind of rewriting, it is easy to lose an important limitation or add a claim that was not in the original content. This is why a post is checked as a separate output.
Runs on the approved document only.
Publishing waits until step 14 is live and verified.
-
BaseHuman Platform rules
Base · Human
Platform rules
Every channel needs its own playbook: format requirements, platform conventions, access rights, legal limits, metrics and a review date.
There is no need to research the format of LinkedIn, Telegram or any other platform again for every article. The playbook is kept as a separate working document.
-
S1Generator Adaptation
Step S1 · Generator
Adaptation
The format comes from the platform playbook. The content uses only claims from the approved document.
Unapproved content is not published.
-
S2Checker Checking the derived content
Step S2 · Checker
Checking the derived content
Every fact is linked to a claim ID again. The checker looks at:
- whether a new fact appeared in the headline, the hook or the caption;
- whether important limitations survived the shortening;
- whether the meaning of the original claims changed.
After the check, an editor approves the content.
-
S3Code Publishing
Step S3 · Code
Publishing
The content is published through an API without any calls to generative models. Publishing starts only after the main page has gone live and passed its post-publication comparison.
When the article is updated, the system automatically marks related content for a new check.