Evidence

Real decisions. Shown work. Scored against reality.

Seventeen documented case studies — each with the actual delivered report attached. Rival AIs reviewing us, history re-run blind, fraud hunts at enterprise scale, and the splits we published instead of smoothing over. These are internal and adversarial stress tests, not paid client engagements, and we say so on every page.

17documented case studies with delivered reports
3 cloudsevery case run on models across Amazon, Microsoft & Google
Preserved dissentsplits published, never averaged away
01

Would an AI Panel Have Caught Lehman's Repo 105?

We ran the Lehman Brothers investment decision through a multi-cloud AI panel twice, with no hindsight in the prompt. It named Repo 105 unprompted and said walk away.

Read the case study →
02

Can AI Read 500,000 Emails and Find Fraud?

We read 45,320 real Enron executive emails blind - deduplicated from 517,401 - in about 2.5 hours for roughly $69, and surfaced LJM, Raptor and Chewco.

Read the case study →
03

AI for M&A Due Diligence on a 10,000-Page Data Room

An AI read a 10,000-page M&A data room in full and surfaced all eight planted deal-breakers, then returned a decisive renegotiate with escrow conditions.

Read the case study →
04

AI Platforms Reviewed by Rival AI Models

We let Google's Gemini act as a hostile client, drive a full decision case, and then write its own review of the output. We published it verbatim, criticism included.

Read the case study →
05

We Let ChatGPT Run a Decision Case and Review Us

OpenAI's ChatGPT drove an entire 3Dogs Nexus engagement as the client, answered both clarification rounds, then wrote a review we published unedited.

Read the case study →
06

AI Probability Forecast: Will Oracle Get a Government Bailout Over Its OpenAI Bet?

32 AI models across 12 vendor families and 3 clouds examined Oracle's BBB- downgrade and OpenAI concentration, and produced explicit odds rather than one opinion.

Read the case study →
07

Pay the Ransom or Rebuild? 23 AI Models Split

A critical-infrastructure ransomware decision run across 23 AI models on three clouds. The panel split 10-to-9 and we published the split rather than hiding it.

Read the case study →
08

Should You Pay a Ransomware Demand?

Two Las Vegas casino operators faced the same attacker in 2023. One paid, one refused. We put the decision to a 13-model panel and it split 5-5-3 - which is the honest answer.

Read the case study →
09

Is the AI market about to crash like the dot-com bubble? What 22 AI models concluded

We asked 22 AI models to compare the AI boom to the dot-com bubble and put odds on ten named scenarios. They put Dot-Com Replay at 1% — and one model held a REJECT at 95% confidenc

Read the case study →
10

Can AI Analyze a Decision in Any Language?

A real EUR12B decision brief submitted in Greek and Mandarin, clarified in Pitjantjatjara and answered in French - the recommendation came back in clear English with every number i

Read the case study →
11

AI Fraud Detection: Our Own Model Voted to Reject Us

Run on the MIT AI research scandal, our permanent adversarial seat voted against the panel's own premise - the clearest evidence the challenger role is real, not decorative.

Read the case study →
12

AI That Refuses to Fabricate: The Deloitte Re-Run

Most AI invents something when the evidence is thin. We ran a well-documented public AI failure through a multi-model panel to see whether ours would decline instead.

Read the case study →
13

What Does the Deepest Multi-Model AI Analysis Do?

Our deepest analysis mode run on a real capital decision, with every step observable: two full ensembles, multiple research passes, and one decisive call.

Read the case study →
14

AI Forecasting With Probability Ranges

Ask one AI to forecast and you get a single confident number. A multi-model panel returns a calibrated probability spread with the dissent preserved and a resolution date to score

Read the case study →
15

Can AI Re-Litigate Military Decisions?

Four of the most-taught command decisions in military history, given to a multi-model AI panel with none of the hindsight, then compared against what actually happened.

Read the case study →
16

Which Road-Safety Projects Should a State Fund?

A 12-model AI panel ranked state DOT road-safety projects and produced the audit trail behind the ranking, including a Bayesian crash-modification-factor condition.

Read the case study →
17

Should a City Fund a Grocery-Access Study? AI Analysis

Before spending incentive dollars on a grocery store, a 12-model AI panel recommended testing operator appetite first - and named that as the dominant risk.

Read the case study →
WATCH

Watch a real case run end to end

Question to signed report — the research, the debate, and the preserved dissent. Rex explains it on YouTube.

Watch on YouTube →