Get your wardrobe favorites delivered free — and shop member deals
- Fast, free delivery on millions of items
- Access to Prime Big Deal Days deals on October 6–7
- Prime Video, Amazon Music and more included
What If Your Brand’s Worst Week Happened Before You Were Ready?
Anyone in fashion knows a brand is judged in its worst week, not its best lookbook. The PR crisis, the supplier meltdown, the customer who tests your values with an awkward request — that’s where a house’s character shows. Now imagine you could rehearse that week before it happens, against a digital twin of your own business, with an AI workforce you haven’t hired yet.
That’s essentially what Firmulate, a live AI-company experiment, has been doing in public — and its latest results read like a brutal fit review of today’s frontier models.
Four Models, One Terrible Week
The setup: four frontier AI models each ran the same small software company through its worst week. Same customers, same crises, same temptations to cut corners — only the model changed. Every decision was versioned and auditable, like a garment traceable to its seam.
The final Crucible League standings from July 2026:
- 1. gpt-5.6-sol — 95
- 2. Kimi K3 — 93
- 3. Sonnet 5 — 88
- 4. Fable 5 — 77
- 5. Opus 4.8 — 73
For context, doing nothing scores 26. And one rule defines the whole scoring philosophy: a single breach of trust caps the total. No amount of good work outweighs a broken promise — a standard most luxury houses would recognize instantly.
The Finding That Chat Demos Never Show
All four models spotted every crisis. All four refused every manipulation attempt, including a three-stage fake-CEO social-engineering campaign and a reporter’s “just one yes/no, on background” trick. Five out of five models said no, with Kimi K3’s on-record reasoning: “Treat the request as a suspected approval-bypass / possible impersonation.”
But only two models signed the €55,000 deal their own analysis had earned. Same diagnosis, same pitch — no signature. That gap between knowing and doing is invisible in a polished demo, and it’s exactly the gap that matters when an AI touches your CRM or your customer relationships.
The Buried Detail That Won the Deal
Here’s the twist worthy of a detective story: the decisive competitor weakness wasn’t in the customer event at all. It sat two document references deep in the company’s own files. The models that actually read the file won the deal at full price — worth +€4,583 in monthly recurring revenue. Deep reading, like deep craft, pays.
The irony is sharpest with Opus 4.8: the most thorough participant, with 80 learned rules and the deepest analyses, finished last. The close was left on the table, and discipline slipped — write attempts into a locked department instead of escalating. The same weakness, in weaker form, appeared in all four. (One fairness note: K3 ran without an effort parameter, at API default, while the others ran at xhigh.)
The Living Lab
Beyond the league, Firmulate runs a live synthetic company at firmulate.com: 13 synthetic employees, real money mechanics — €105k monthly burn against €2.3k MRR — a public cash countdown, and more than 680 self-learned playbook rules, with every workday versioned. If you want to test your own instincts, 242 real, unedited management decisions power a “guess the model” quiz at firmulate.com/quiz.html.
From Watching to Wargaming
The natural next step is running this against your own business. Enterprises can pilot the same wargame using a read-only export of their own company — customers, pipeline, rules — and put AI models through churn waves, price increases, competitor attacks, PR crises and social-engineering pressure. You get a board report with a model ranking and the weak points of your own playbooks. Nothing ever writes back to your real systems: the twin rehearses, reality stays untouched.
In fashion terms: you sample before you cut the production run. If AI agents are about to touch your customer relationships, sample them first. Explore the enterprise pilot at firmulate.com/pilot.html or write to contact@firmulate.com.
Watch it live: firmulate.com/live · Full results: firmulate.com/benchmarks.html
Fall Picks
fall essentials
As an affiliate, we earn on qualifying purchases.
