Use case · Citations
When the AIs answer your topic, do they read you?
Media, experts, documentation: your pages compete to be the bibliography of your topic. Epovest measures which sources the engines actually cite, yours among them, and shows where to push next.
Views from the app. Your figures replace the sample at the first survey.
The question flips: from what they say to where they read
Every check archives the sources each engine cited on your prompts. Your domain's appearances in those bibliographies are the measure: which engine reads you, on which questions, next to whom. The same map ranks every other source feeding your topic, so the gap between you and the reference above you is readable, engine by engine.
What you measure
Your domain among the cited
Each check records the sources behind every answer: yours are there to be read, dated, prompt by prompt.
Your AI Authority
The weight of your domain in each engine's citations, on the same scale as every other source of your topic.
The topic's bibliography
The full ranking of sources the engines lean on for your questions: who you stand next to, and who is rising.
Entering and fading sources
The freshness reading shows which domains are entering the answers and which are dropping out, check after check.
The recipe
How to grow your pages into cited sources with Epovest
The full working guide for this use: the flipped question stated first, prompts your pages answer, citable pages, your domain's authority on the Atlas, and the chronicle that ties publishing to citations.
State the flip: you are the source, and the citations are the score
The uses on the other pages watch a NAME in the answers. This one watches domains in the citations: yours.
Concretely: your name needs no place in the prompts, and can even stay out of the keywords. The prompts are your topic's questions; the reading is the cited-sources record of each answer, and your domain's line in it. If you also sell under your name, run that as a separate reputation or ranking tracker: the two readings stay clean.
The prompts: the questions your pages answer
Ask what your readers ask the engines, on the ground your content covers. Wherever the engines cite sources, there is a bibliography to enter.
"How do I choose [what your guides compare]?"
"What are the latest figures on [your beat]?"
"Explain [the topic your reference pages cover]"
"Is [the claim your investigation checked] true?"
Five to ten prompts, one per flagship page or content family. Phrase them the way readers do, in your audience's language: an engine cites different sources in different languages, and your measure should live where your readers ask.
Pages an engine can cite
A citable page states its facts plainly, dates them, and holds an answer where an engine looks for one. The surfaces registry keeps your flagship pages in that state.
Register your flagship pages, the guides, the studies, the reference articles, as surfaces, and let each checklist carry them to citable: canonical facts stated, dates visible, llms.txt in place for the domain. When your editorial line evolves, the registry names the pages left behind: a stale flagship is the first citation you lose.
Your domain on the Atlas: the score is its AI Authority
The Atlas ranks every source your topic's answers cite. Your domain sits in that ranking like any other, with an AI Authority per engine.
Read your line engine by engine: an engine that cites you weekly and one that has never read you are two different jobs. Above you, the ranking names the references your topic trusts; the freshness sort shows who is entering. Both readings point the same way: which questions to cover next, and which engine's bibliography to work first.
A republication is a corroboration: record it
When another site quotes your study or republishes your figures, that page pushes your topic's answers too. It belongs in your register.
Record each reprise as a corroboration: the page, its date, the piece it cites. Verification archives the passage around the reference; monitoring, weekly on the heavy ones, tells you if the quote or the link drops. Candidates surface what you missed: the pages where engines already showed your domain in their answers, ready to record.
The chronicle: publish, date, confront
This use has a natural rhythm: you publish, the engines read, the citations move. The Logbook keeps the three in one timeline.
Date every piece you publish, every republication obtained, every revision of a flagship page. The citation series then reads with its causes in front of it: which piece entered the bibliography, how long an engine took to pick it up, which revision revived a fading page. Quests keep the rituals: reread the freshness monthly, requeue the fading flagship, cover the question the top source leaves open.
Worked example
A study enters the bibliography
You publish your annual study; the prompts it answers are already in the tracker, and the Logbook dates the release. The following checks find one engine citing it on two prompts; candidates surface a newsletter that republished the key figure, recorded as a corroboration and monitored. The freshness reading shows your domain entering that engine's bibliography, and the fading source above you names the question your next piece should cover.
With your AI assistant
Your AI assistant runs this recipe with you
Connect Epovest to the assistant you already use, one-click connector or API key. It creates trackers, reads the results and keeps the registers with you; a payment only ever happens with your approval.
The instruction to give it
Connect to Epovest and set up a citations tracker for [my publication]: eight prompts our pages answer, discovery on, weekly in hd. At every check, read which sources each engine cited, flag our domain's appearances, and keep the reprises of our work recorded as corroborations.
$0.10
per prompt, per engine, per check
Pricing
Whatever you configure, the unit never changes. Your total shows live in the configurator before anything runs; you start whenever you want, from a $10 top-up. No subscription: only the checks that run are debited.
A new piece enters the watch in one gesture
Publish a study, add the prompts it answers to the tracker: the next checks tell you which engines picked it up. The series continues, version after version.
The other use cases
Make AIs recommend you
Create a tracker in minutes: your prompts, your engines, your cadence. First checks within 24 to 48 hours.
No subscription. Credits from $10, valid 12 months. Pause anytime: the history stays yours.