Cerberus
Start free
Cerberus · pre-publish citation intelligence

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.

Engine
15 deterministic signals · 3 advisory heads
Probe
live answer-engine check on published pages
Plans
Free · £75/mo Pro · £140/mo Agency
Status
founding cohort · by invitation
The offer

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.

Four principles

The rules the design refuses to break.

01 · confidence

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.

02 · provenance

"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.

03 · correction

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.

04 · restraint

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.

The surfaces

What the founding cohort is shaping.

01
Live today · per-piece surface
The three-column editor: manuscript on the left, scored passages in the middle, inline recommendation and receipts on the right. The user never loses their place in their own text.

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.

Anchor model: passage-level, not paragraph-level
Recommendation carries: cohort, lift, interval, preview
"Why this": unfurls on the same page, never a modal
Override: reachable in one click from any card
02
Prototype · command surface
The daily page. Visibility score, the citation trend, and the day's 3 top recommendations - each with visible confidence and a one-click Apply. Month-3 and month-1 states toggle from the header.

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.

Hero metric: citation-worthiness, not vanity score
Trend shape: sparkline with interval ribbon
Cold-start: honest "not enough data yet" state
Recommendations: high / medium / low tiers, never mixed
03
Prototype · reflective surface · A + B
The "What I've Learned" page - two interchangeable treatments of the same data. Readers toggle between them from the top-right of either page.

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.

Both support: inline correction, evidence reveal
Contested observations: kept, struck, quoted verbatim
Confidence spine: preserved across both treatments
Trade: editorial rewards skim; portrait rewards sit
04
Prototype · component gallery
The recommendation card in its three tiers, three variants, and four states. The atomic coaching unit, shown in every room of the product.

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.

Tiers: high (Apply), medium (Preview), low (verify first)
Variants: canonical, inline, digest
States: default, applied, dismissed, flourish
Champagne: used for exactly one state - a tier-crossing
05
Prototype · trust contract
The four-frame override sequence: the recommendation in context, the dialog, the corrected state six seconds later, and the receipt visible fourteen days on. The heart of the product.

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.

Dialog: reason chips + sentence + scope + visible weight
Scope: one piece, one pattern, or one whole topic
Corrected card: original struck; correction quoted verbatim
Receipt: appears in the Portrait trail, permanent
06
Prototype · accountability surface
Every applied recommendation, reconciled against its predicted interval. A calibration chart, a ledger, and three cohort-reliability panels- the model's annual review, written by the user's own work.

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.

Calibration: predicted interval vs observed outcome, 30d windows
Ledger: every applied rec, expandable for provenance
Cohort cards: reliable, provisional, contested
Tone: owns its errors, names its thin samples
Plans

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.

Free
Free
no card required
  • 10 evaluations / day
  • 1 project
  • no citation testing
Pro
£75/mo
£60/mo billed annually
  • 200 evaluations / day
  • unlimited projects
  • 20 citation tests / day
  • batch scoring, 20 at a time
Agency
£140/mo
£112/mo billed annually
  • 1,000 evaluations / day
  • unlimited projects
  • 50 citation tests / day
  • batch scoring, 50 at a time
Colophon
Set in Instrument Serif for editorial voice, Bricolage Grotesque for UI, JetBrains Mono for metadata. Colours drawn from stone neutrals with a single champagne accent. No gradients, no faux-glass, no ambient glow. Prototype surfaces above carry example data and say so; every number in the product itself is computed from your content, or absent.
cerberus · aspect research ltd · 2026