Know if AI will cite you
— before you publish.
Fifteen deterministic citation signals score a draft before it ships; a live answer-engine probe verifies the published page — cited, or not. The pre-publish complement to the monitoring dashboard you already own.
Answer engines now sit between your content and its readers. Whether ChatGPT, Perplexity, or Google's AI Overviews cites your page decides whether it is read — and most teams learn the answer after publishing, from a monitoring dashboard, when the piece is already live.
Cerberus is the gate before that. Paste a draft: fifteen deterministic signals score its citability and name exactly what fails — the same checks every run, no model variance. Three adversarial heads — Critic, Advisor, Guardian — argue the why: what to cut, what to keep, how to pass.
When the piece goes live, the probe asks a real answer engine the queries you care about and records the verdict — cited, or not. The score is the prediction; the probe is the receipt. Cerberus is proving that loop with a founding cohort of B2B content teams — by invitation — while the score stays free for anyone, no account needed.
The rules the design refuses to break.
Confidence is a spine, not a decoration.
Every number, every recommendation, every observation declares its tier - high, medium, low - in the same place, the same way. The spine never moves, across all five surfaces.
"Why this?" is always one click away.
Cohort size, model version, base rate, interval, the specific examples that drove the inference - none of it is buried, none of it is inferred. The receipts are always shown, not assumed.
Disagreeing is a first-class verb.
Override isn't a rare admin action - it's how the product learns. The weight of every correction is visible before it's saved, and stays in the log forever after.
Champagne is a flourish, not a filler.
Colour is reserved for single moments - a threshold crossed, a scope highlighted, a correction weighted. Otherwise the surface is stone. The less we say, the more each word carries.
What the founding cohort is shaping.
Scoring that reads the prose, not the metadata.
Each scored passage is marked in the manuscript itself, anchored to the sentence it concerns. The score is a conversation between the writer and the model, not a verdict handed down from outside the text.
A dashboard that starts with why you should trust it.
The visibility number never travels alone: it carries its 90-day trend, its cohort, and its confidence interval. Built for readers who look, not glance.
Two ways of hearing the same portrait.
Seventeen observations about a writer's voice, audience, and how AI systems quote them — the same data in two treatments. Editorial is a magazine spread; Portrait is a letter.
One card, many rooms, one shape.
A recommendation appears on the dashboard, inline in the editor, on the tracker, and in the digest. The affordances compress; the contract — confidence, evidence, predicted lift, override — does not.
Disagreeing, all the way through.
The override dialog shows, in plain numbers, how much weight your correction will carry — before it is saved. The corrected card never vanishes, and the log speaks back later.
The model's reckoning with its own predictions.
Most tools stop predicting once the change is applied; Cerberus holds itself to the prediction. When the model is wrong, the ledger says so; when a cohort is thin, the cohort says so.
One engine, three volumes.
Founding-cohort phase: the Free plan is open to everyone; partner seats are by invitation and free while the phase runs. Billing opens when it closes.
- 10 evaluations / day
- 1 project
- no citation testing
- 200 evaluations / day
- unlimited projects
- 20 citation tests / day
- batch scoring, 20 at a time
- 1,000 evaluations / day
- unlimited projects
- 50 citation tests / day
- batch scoring, 50 at a time