// Parallel preview — nothing on the classic site is replacedView classic site →
// MIZOKI3 SIGNAL · Marketing & media buying · transparent by design

Anticipatory marketing intent — with proof, not promises.

Signal turns ad platforms, analytics, your site, and inventory into governed evidence: what is about to happen, what actually caused what, and which spend earns its keep. The deepest division today — and the home of the media-buying stack.

What we say

Calibrated probabilities and proof of causal lift. Targets labeled as targets, and a credit ledger that separates what marketing caused from what it merely anticipated.

What we never say

"Mind-reading." "This account will buy." Audio capture — ever. Predictions are probabilities, not promises.

// The contract, in plain terms

What it watches. What it decides. What it never does.

Every division runs the same 7-Stage Governed Decision System, under the same Safety Guardrail Engine, writing to the same Compounding ROI Memory. Here is Signal's slice of it — stated plainly, so you can hold us to it.

Watches
  • Campaigns, auctions, and creative delivery
  • Site, pixel, and tracking health
  • Inventory and sell-through
  • Margin and ROAS guardrails
Decides
  • Reallocations toward proven-incremental spend
  • Pauses and negative keywords with evidence attached
  • Quarantines of metrics that fail evidence checks
  • Vetoes when a floor would be breached
Never does
  • Acts on a metric that failed its evidence check
  • Spends past your floors
  • Claims credit without causal proof
// Show, don't tell

A real decision, from the real desk.

Not a mockup — the live desk runs the production runtime, seeded and replayable, and this is one of its decisions.

From the live desk — the honest refusal

Pixel fires drop 35% overnight; orders are flat. A naive automation slashes budgets against the broken number. Signal quarantines the metric, evaluates the ROAS floor on verified server-side evidence, and holds spend steady — the correct move is refusing the panic cut.

Illustrative scenario data · deterministic and seeded — replay it yourself on the live desk.

// Media acquisition intelligence — software facts, not marketing memory

The acquisition stack, with its real numbers.

Every figure below is read from the Boss modules that actually run — the Signal Factory engine, its guardrail set, and the simulator — or labeled as platform spec where the capability ships observe-first. The test suite asserts this page against the code: if an engineer changes a floor, this page fails the build until it tells the truth again.

ReLU threshold intelligenceLive in the demo

The gate is max(0, uplift): weak evidence is zeroed, never averaged in. A segment must clear all three floors — measured uplift, decision confidence, and sample size — before it may carry budget.

Operating defaults — uplift floor 5% · confidence floor 0.70 · sample floor n = 15
source: demo_signal.GATE_UPLIFT_FLOOR · GATE_CONFIDENCE_FLOOR · GATE_SAMPLE_FLOOR

ReLU-gated budget reallocationLive in the demo

Budget moves only through cleared gates, and swings are capped in the Validate stage. The demo deliberately requests a +25% swing so you can watch the guardrail block it — the part most demos hide.

Operating defaults — budget swing cap ±20% · bid swing cap ±30%
source: demo_signal.GuardrailSet.BUDGET_SWING_CAP_PCT · BID_SWING_CAP_PCT
▶ watch the +25% request get blocked (seed 42)

Value-based biddingLive in the demo

Every proposed action is a value object, not a hunch: it carries expected value, decision confidence, and the conversions supporting it. In the seeded run, the winning move is +12% on campaign_7 — because the numbers say so.

Operating parameters of the seeded run — winning action +12% campaign_7 · expected value $8,400 · confidence 0.86 · support n = 48
source: demo_signal.SCENARIOS["ecommerce_roas"].planned_actions (seed 42)

Creative fatigue — diagnosed, not assumedLive in the simulator

Fatigue is a verdict, not a reflex. When creative CTR is flat while post-click conversion falls, the cause is the site, not the creative — the simulator's Reason stage makes that call in front of you. Real-time fatigue tracking ships in the Meta & Paid Social module.

diagnostic rule flat CTR + falling post-click CVR → not creative fatigue
source: media-sim.js modelLatency reason chain · Meta module (spec)
▶ trigger the diagnosis yourself

Uplift pacingPlatform spec

Spend paces to modeled incremental lift per segment — X-Learner and DR-Learner estimate who is actually persuadable — so budget concentrates where dollars change outcomes, not where platforms claim credit.

estimators X-Learner · DR-Learner · optimization target iROAS, not platform ROAS
source: Signal Intelligence spec §7.1 / §4.1 · observe-first until promotion gates clear

Uplift audiencesPlatform spec

Lookalike expansion with the upgrade classic lookalikes lack: every candidate carries a calibrated intent probability and stage — awareness, consideration, in-market, purchase-imminent — so you expand toward people approaching in-market, not people who merely resemble your seed.

method two-tower embeddings + nearest-neighbor retrieval · stages 4, calibrated
source: Signal Intelligence spec §4.4 / §6 · consent-gated ingestion, always

Attribution & measurementQuarantine live · designs spec

Multi-touch attribution calibrated by experiments — holdout, ghost-bid, geo — with every causal estimate stress-tested by DoWhy refuters before it is trusted. And when a feed lies, it is quarantined: the demo's e-mail scenario refuses proxy-open inflation at the gate; the simulator defends the ROAS floor on verified 3.1× evidence when pixel fires drop 35%.

refuters placebo-treatment · random-common-cause · data-subset · ledger caused vs anticipated
source: spec §7.2–7.3 · demo_signal email_reengagement · media-sim.js PIXEL_DROP / VERIFIED_ROAS
▶ watch the proxy-open quarantine (seed 42)

Promotion gates & consentGovernance, always on

Anticipatory models ship observe-only and are promoted to autonomy only past explicit calibration gates. Micro-signal ingestion sits behind a hard consent gate — no consent, no ingestion, no exceptions. Outcome figures on this site are design targets, labeled as targets, never outcome promises.

promotion gates Brier ≤ 0.20 · AUC ≥ 0.72 · stable lift ≥ 2 cycles · serving sub-100ms
source: Signal Intelligence spec §6.4 / §5 · observe-only default
// Operating parameters — read from the software

The numbers, with their source of truth.

Pulled from the modules that run the demos and the simulator. The suite's sync test imports the runtime and fails if this table drifts from the code.

ParameterValueSource of truthSee it run
ReLU uplift floor5%demo_signal.GATE_UPLIFT_FLOORsignal desk →
ReLU confidence floor0.70demo_signal.GATE_CONFIDENCE_FLOORsignal desk →
ReLU sample floorn = 15demo_signal.GATE_SAMPLE_FLOORsignal desk →
Budget swing cap±20%demo_signal.GuardrailSet.BUDGET_SWING_CAP_PCTthe block →
Bid swing cap±30%demo_signal.GuardrailSet.BID_SWING_CAP_PCTthe block →
Replay seed (shared runs)42demo_signal.DEFAULT_SEEDsignal desk →
Target ROAS floor2.2×media-sim.js ROAS_FLOORsimulator →
Max auto-spend limit$5,000media-sim.js MAX_SHIFTsimulator →
Pixel-drift stress case−35% fires · verified 3.1×media-sim.js PIXEL_DROP · VERIFIED_ROASsimulator →
Model promotion gatesBrier ≤ 0.20 · AUC ≥ 0.72 · lift ≥ 2 cyclesSignal Intelligence spec §6.4 (observe-only default)governance →

Live-in-demo figures are executable — same seed, same numbers, every run. Platform-spec figures come from the owner's Signal Intelligence specification and ship observe-first behind the promotion gates above. Design targets stay labeled as targets.

See Signal decide — live.

The desk narrates its own run: the checks, the gates, and the moment it commits or holds. Same runtime that ships.