The Engine That Refuses to Lie

Document Type: Validation Case Study

Test Date: May 2026

Test Organizations: 2 Independent Businesses

Data Quality: Real-World, Flawed

Permission: Granted by All Parties

Most marketing analytics tools display confident numbers on incomplete data. CDAI does the opposite: when the data isn't trustworthy, the engine flags it and refuses to issue directives. Here's what happened when we ran it on two real businesses with real data quality problems.

This document is not

Not a recovered-dollars story. CDAI's full margin output requires complete cost stack data. One of the two businesses below has incomplete cost data; the engine handled that correctly — which is the point.
Not a third-party competitor takedown. Existing tools solve real problems. CDAI solves a different problem.
Not a prospective claim. Everything below has happened. No projections, no pro-forma.

The Question Every CFO Asks

"How do I know your tool isn't just hallucinating numbers?"

It's the question that kills analytics deals. Sophisticated buyers — CFOs, in-house data teams, finance committees — have seen too many dashboards confidently display figures that don't survive a five-minute audit. The MarTech category is full of tools that calculate ROAS to two decimal places on data they don't actually have.

CDAI was built specifically against that failure mode. The engine measures one thing — true contribution margin per campaign, after every cost layer the platforms don't report — and issues one of eight enforceable directives: SCALE, HOLD, CUT, PAUSE, QUARANTINE, RENEGOTIATE, INVESTIGATE, FLAG.

This document is an operational record. Two real businesses, real data, real engine output. What the engine did. What it refused to do. Why both matter.

Read Case Study #2: OAuth Validation

What CDAI Measures

Most marketing analytics tools answer the question: "What did this campaign return in revenue divided by ad spend?"

CDAI answers a different question: "What did this campaign actually contribute to the bottom line, after every cost the platforms don't report?"

The Seven-Cost Stack

Platform-reported cost-per-lead and cost-per-acquisition reflect only the costs the platform controls — its own media spend. CDAI reconciles all seven cost layers visible in real lead-gen and acquisition operations:

Cost Layer	Visible to Google / Meta?
1. Media spend	Yes — the only layer the platforms accurately report
2. Platform fees	Partial — platform-side fees only, not third-party tooling
3. Broker payouts	No — agency margin and lead vendor fees are invisible to platform reporting
4. Refunds	No — post-conversion refund data sits in finance systems, not ad systems
5. Chargebacks	No — payment processor data, weeks-to-months delayed
6. Compliance costs	No — TCPA, HIPAA, state-specific compliance overhead never enters ad reporting
7. Variable costs	No — intake fallout, sales close rate, fulfillment cost

In real operations, the gap between what platforms report (layer 1, sometimes part of layer 2) and the true cost-per-bound-acquisition can be 30 to 70 percent. The campaign that looks profitable on a Google Ads dashboard is often the campaign that's quietly destroying margin once the full cost stack is reconciled.

Test Case 1: FullSend Organicks LLC

The Test

The business ran a Google Search Ads campaign from August 31, 2025 to December 2, 2025. The campaign was complete (concluded), with full historical data exportable from Google Ads.

Test Parameters

Data source: Real exported Google Ads CSV Campaign period: August 31, 2025 – December 2, 2025 (~94 days) Total spend: $2,112.17 Conversions: 37 reported Ingestion method: Direct SQL via ingestion_pipeline.py Data age at test: ~4 months stale

What the Engine Did

✓ Step 1: Ingestion

Successfully Loaded Real Platform Data

Engine connected to live Supabase production database. Real Google Ads export ingested via SQL into the campaigns table. Campaign and cost event records inserted with correct org_id binding. No errors. This confirms the engine can read real exported platform data — not just demo fixtures.

✓ Step 2: Calculation

Ran Directive Logic Without Runtime Error

Engine successfully read campaigns from the database, attempted contribution margin calculation, and ran the directive logic end-to-end without runtime error. The 0% CM result is a data-completeness condition — the engine reflected what it was given. A tool that confidently displays a margin figure on incomplete cost data is hallucinating. CDAI did not.

✓ Step 3: Health Monitor

Engine Refused to Issue Directives on Stale Data

Before issuing any directives, CDAI runs a health monitor evaluating data freshness, completeness, and integrity, then sets a single boolean: directive_safe.

On this data, the monitor identified the campaign as approximately four months stale and set directive_safe = FALSE. The engine refused to issue directives.

A SCALE directive issued on stale data is worse than no directive at all — it tells a marketer to commit budget to a campaign whose underlying conditions may have changed. CDAI's health monitor exists specifically to prevent that failure mode.

✓ Step 4: Multi-Tenant Isolation

Zero Cross-Organization Data Leakage

The data was ingested into its own organization within the multi-tenant Supabase architecture. Row-Level Security policies were active. Subsequent queries filtering by org_id returned only this organization's data — no cross-organization data appeared, even when running against the same database containing other test organizations.

What This Validates:
• CDAI ingests real exported platform data without modification or fabrication
• The engine does not invent values for cost layers that aren't populated
• The health monitor functions as a safety gate — directives do not issue on data the engine cannot stand behind
• Multi-tenant data isolation works on real data, not just architecture diagrams

Test Case 2: Apex Care Solutions LLC

The Test

The business provided 3.5 months of Meta Ads Manager exports from January 1, 2026 to April 22, 2026, plus a CRM contacts file. The data represents a real-world condition: recent, operational, and with one critical attribution gap.

Test Parameters

Campaigns ingested: 7 Cost events ingested: 8 Total Meta spend: $2,414.12 Total impressions: 62,211 Lead records received: 276 contacts in CRM export Lead records ingested: 0 — see analysis below

What the Engine Did

✓ Step 1: Multi-Tenant Setup

Production Architecture Verified

New organization created in the orgs table. Meta Ads channel created and bound to the org_id. Client user account created and linked via the client_users table. Row-Level Security policies confirmed active on every data table.

Cross-tenant isolation verified: Apex's data was inserted into the same physical database already containing FullSend Organicks' data. Queries filtering by org_id returned only Apex data. The architectural isolation works on real client data — not just in test fixtures.

✓ Step 2: Campaign & Cost Ingestion

Data Preserved Exactly As Exported

Seven Meta campaigns ingested via SQL, all tagged with the correct org_id. Values preserved exactly as exported from Meta Ads Manager — no alterations, no inferred values, no fabricated columns to fill gaps.

When a CSV has a missing column, the easy path is to fill it with a sensible default and keep going. CDAI does not.

✓ Step 3: The Lead Attribution Gap

Engine Flagged Missing Attribution — Refused to Invent

The CRM contacts file contained 276 lead records. The Source column on every lead read "Contact Import" — no campaign attribution existed at the lead level.

Without attribution, the engine cannot calculate true cost-per-lead by campaign or issue directives at the campaign level. The engine did not attempt to fabricate the attribution it lacked. Lead records were not ingested. The audit pipeline halted at the data quality gate.

A weaker tool would have ingested the leads with null campaign_id values, used a heuristic to invent attribution, or issued directives anyway with a footnote. CDAI did none of those.

✓ Step 4: Health Monitor

Refused to Issue Directives on Incomplete Data

With incomplete attribution upstream, the health monitor flagged the data set as not directive-safe. directive_safe = FALSE. No directives were issued.

Same behavior as Test 1 — different trigger condition (stale data vs. missing attribution), identical engine response: refuse to issue directives the data cannot support.

What This Validates:
• Multi-tenant isolation works on real client data in production against a database already containing other organizations
• The engine does not fabricate attribution to fill gaps — it surfaces the gap as a finding
• The health monitor responds to multiple distinct integrity failure modes, not just one
• CDAI's data quality discipline is structural, not optional

The Verification Layer

Every number in this document is queryable. The three SQL queries below were run directly against the live Supabase production database. Nothing was asserted without a query to back it up.

Query 1 — Campaign count and total spend

SELECT COUNT(*) as campaign_count, SUM(ce.spend) as total_spend FROM campaigns c JOIN cost_events ce ON ce.campaign_id = c.campaign_id WHERE c.org_id = '8d9b345c-4617-4d6a-977a-8fea8684bc61';

→ campaign_count = 8, total_spend = 2414.12

The 8 cost events against 7 campaigns is explained by Meta's export format: 'New Leads Campaign' ran as two separate ad sets. The $2,414.12 matches the source CSV exactly to the cent.

Query 2 — Lead record count

SELECT COUNT(*) as lead_count FROM lead_events WHERE org_id = '8d9b345c-4617-4d6a-977a-8fea8684bc61';

→ lead_count = 0

Zero lead records in the database. Confirmed. All 276 contacts in Apex's CRM export had 'Contact Import' as the source field — no campaign attribution. The engine correctly refused to ingest them.

Query 3 — Campaign names and status

SELECT campaign_id, name, status FROM campaigns WHERE org_id = '8d9b345c-4617-4d6a-977a-8fea8684bc61' ORDER BY name;

→ 7 named campaigns returned: Calendly Instant Book · Community Education Event · In-Home Care Ad New Leads Campaign · Open Rooms Now at Senior Care Home in Guilford County Sensi Solo Care · Test - Sensi Solo Care

No blank-name row. The totals row in Meta's CSV export format was correctly excluded by the ingestion pipeline.

What These Two Tests Prove Together

Two real businesses. Two different industries. Two different platforms (Google Ads and Meta Ads). Two different data quality problems. One consistent engine behavior.

Test Dimension	FullSend Organicks	Apex Care Solutions
Platform	Google Ads	Meta Ads
Industry	E-commerce	Healthcare / senior care
Data Condition	Complete but ~4 months stale	Recent but missing campaign attribution
Ingestion	Successful	Successful (campaigns + costs); halted on lead attribution gap
Multi-Tenant Isolation	Verified	Verified
Health Monitor	`directive_safe = FALSE` (stale)	`directive_safe = FALSE` (incomplete)
Directives Issued	None — by design	None — by design
Fabricated Values	Zero	Zero

The Behavior Worth Naming

CDAI is built on a principle that's rare in the marketing analytics category: the engine refuses to issue an output it cannot stand behind.

The competitive landscape is full of tools that confidently display modeled conversions, attributed revenue, and projected ROAS — calculated on data with significant integrity issues, presented without any indication that the underlying inputs were incomplete or stale. Most CFOs evaluating these tools have learned to discount the headline numbers by 30 to 50 percent before believing them.

That refusal-to-fabricate behavior is the single most important property an analytics engine can have when the buyer is a CFO with budget authority and a long memory for tools that lied to them.

What CDAI Looks Like With Complete Data

So that the integrity-first picture above isn't mistaken for a limitation, here's what CDAI's full output looks like when the cost stack is populated and the data is current.

In a separate prior test, the engine was run against a complete data set — six campaigns, full seven-layer cost stack populated, all data current. The engine executed end-to-end without error and produced one directive per campaign across all eight directive types:

SCALE — campaigns where true contribution margin justified increased spend
HOLD — campaigns with developing data not yet conclusive
CUT — campaigns where true margin was negative once the full cost stack was reconciled, including one notable PAYOUT_BLEED case where reported CPL looked acceptable but true margin was significantly negative
PAUSE — campaigns showing anomalies under review
QUARANTINE — campaigns with fraud rate exceeding threshold
RENEGOTIATE — campaigns where partner payouts exceeded sustainable margin
INVESTIGATE — campaigns with refund or chargeback anomalies requiring review
FLAG — campaigns requiring human review due to data anomalies

Each directive carries a numeric confidence score and a reason code. The directive sheet is the engine's primary client-facing artifact and is what every paying audit delivers.

Production Evidence — Directive Issuance

directive_events table (live production database): → 121 directives issued across 2 organizations → Span: 32–39 days of directive coverage → All 8 directive types represented: SCALE, HOLD, CUT, PAUSE, QUARANTINE, RENEGOTIATE, INVESTIGATE, FLAG → All directives confidence-scored: HIGH, MEDIUM, LOW → Zero directives issued when directive_safe = FALSE

Production Evidence — Automated Health Checks

system_health table (May 7–8, 2026): → Health checks running automatically on scheduled intervals → 15+ automated entries confirmed with timestamps → All 5 check types executing: cost_freshness, lead_freshness, spend_reconciliation, attribution_integrity, directive_freshness → Scheduler deployed and operational via Render backend

Why This Matters to a Buyer

If you run paid acquisition at any meaningful scale — six figures monthly or more — three things follow directly from these tests.

One · Your reported cost-per-acquisition is structurally incomplete

The platforms report what they control. They do not reconcile broker margin, refunds, chargebacks, or compliance overhead. A campaign that looks profitable in your Google Ads or Meta dashboard is often the campaign that's destroying margin once the full cost stack is reconciled. The 30 to 70 percent gap between reported CPL and true cost-per-bound-acquisition is structural arithmetic — it compounds every month you don't measure it.

Two · The tools that say they fix this often don't

The contribution-margin-aware tools in market today are largely Shopify-native, optimized for ecommerce SKU economics. They do not handle lead-gen broker payouts, regulated-industry compliance overhead, multi-platform partner ecosystems, or refund-and-chargeback dynamics specific to high-ticket services. CDAI is built for these conditions specifically.

Three · The engine you choose has to refuse to lie

If your CFO is going to make capital allocation decisions on the engine's output, the engine has to be willing to tell you when it doesn't have enough data to recommend an action. CDAI does this. The two tests above — and the three verification queries — are the proof.

What's Next — Pricing & How an Audit Runs

CDAI is operating commercially. The Distortion Audit is the entry point most clients use — a deliverable that produces a complete directive sheet from 90 days of your campaign data.

Distortion Audits (One-Time)

Tier	Scope	Turnaround	Price
Quick Audit	Up to 50 campaigns · 1–2 platforms · 30-day lookback	5–7 days	$2,500
Standard Audit	Up to 150 campaigns · 2–3 platforms · 60-day lookback	7–10 days	$5,000
Deep Audit	150+ campaigns · All platforms · 90-day lookback · Full partner accountability · Budget reallocation	10–14 days	$10,000–$20,000

Ongoing Retainers

Tier	Verified Ad Spend	What's Included	Price/mo
Starter	Up to $10K/mo	Automated nightly sync · Monthly directive reports · Portal access · 30-day retest scoring · Email support	$1,500
Growth	$10K–$50K/mo	Everything in Starter · Weekly directive reports · Quality decay tracking · Budget reallocation modeling · Slack + monthly call	$3,500
Scale	$50K–$150K/mo	Everything in Growth · Daily directive refresh · Partner risk scoring · Custom reporting · Weekly strategy calls	$8,000
Enterprise	$150K+/mo	Everything in Scale · White-glove onboarding · Dedicated account lead · Custom integrations · SLA-backed support · Quarterly reviews	$15,000+

How an Audit Runs

Mutual NDA signed, Service Provider Agreement signed.
Client provides 90 days of CSV exports — Google Ads, Meta Ads, LinkedIn, partner channels — plus refund and chargeback data from finance systems and any partner payout records.
CDAI ingests, runs the platform_detector to validate data integrity at the column level, runs the health monitor to confirm data is recent and complete, then executes the full audit pipeline.
Within the agreed turnaround: a complete directive sheet — one directive per campaign, confidence-scored, reason-coded — plus the full distortion analysis showing where reported CPL is hiding true cost-per-acquisition.
The audit deliverable is yours. No consumer PII enters the system at any stage.

The Question That Reveals the Gap

"Do you know your actual cost per signed case after lead vendor margin, intake fallout, and chargebacks?"

If they need a moment: "Let me put it another way: Do you know your true cost per signed case after your lead vendor takes their margin, after prospects fall out during intake, and after refunds and chargebacks hit?"

The people to think about are anyone who runs or owns:

A personal injury or mass tort law firm — spending on lead vendors like EvenUp, Axiom, or Litigation Leaders, or running their own Google/Meta campaigns
An insurance agency or Medicare brokerage — buying leads from aggregators or running direct acquisition
A senior care or assisted living facility — acquiring patients through lead vendors, referral networks, or paid ads
A home services company — roofing, solar, HVAC, water damage restoration — buying HomeAdvisor, Angi, or Thumbtack leads or running their own campaigns
Any business spending serious money buying leads from vendors — if they're writing five-figure monthly checks to lead sources and can't tell you the true cost per customer that actually closes and stays closed

Almost nobody can answer this question. That's the whole point. If anyone comes to mind, a warm intro is all we need — not asking for a pitch, just an introduction so we can ask them the question above.

See What Your Platform Isn't Telling You

Most businesses are making capital allocation decisions on numbers that are wrong by 30–70%. The gap between what your dashboard reports and what you're actually paying is structural arithmetic — it compounds every month you don't measure it.

A 30-day distortion audit on your campaign data starts at $2,500 and delivers within 7 days. If we don't surface margin distortion you weren't tracking, you don't pay.

Request a Distortion Audit

Technical Architecture Summary

The CDAI Engine is deployed on:

Database: Supabase (PostgreSQL) with Row-Level Security policies — multi-tenant capable, 50+ clients simultaneously
Backend: Python on Render (Standard tier — no cold starts, sub-0.5s response)
Portal: React on Vercel (live at cdai-portal.vercel.app)
Scheduler: Deployed and running automated health checks (2 AM UTC nightly sync)
Email Delivery: Operational via Resend — verified domain alloceraintelligence.com
Zero consumer PII stored in any table

Full Methodology Available Under NDA: The detection logic, directive classification engine, and attribution reconciliation framework are original intellectual property. Complete technical disclosure is available to qualified clients and partners under signed NDA.