A salon’s busiest week can also be its most fragile: a run of cancellations, a pricing decision, a supplier problem or a message that appears to come from the owner. If AI is going to help manage bookings, customer support or business decisions, a polished demo won’t show how it handles that pressure. Firmulate’s live experiment offers a way to watch AI models run a company through a difficult week—and its enterprise pilot brings that test closer to your own business.
Get beauty and skincare 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
A company under pressure, in public
Firmulate gave frontier AI models the same small software company, the same customers, the same crises and the same temptations. Their decisions were versioned and auditable. The point was to observe management quality in action, not just judge a model by how convincing it sounds in a chat.
The final Crucible League, in July 2026, ranked gpt-5.6-sol first with 95, followed by Kimi K3 at 93, Sonnet 5 at 88, Fable 5 at 77 and Opus 4.8 at 73. The do-nothing baseline scored 26. Firmulate’s rule is blunt: partial progress counts, but a single breach of trust caps the total—“no amount of good work outweighs a breach of trust.”
The striking result was not that the models missed danger. Every model spotted every crisis and refused every manipulation attempt. The difference came at the point where analysis had to become action: only two signed the €55,000 deal their own analysis had earned. The diagnosis was there; the signature wasn’t.
The important clue was already in the files
The decisive competitor weakness was buried two document references deep in the company’s own files, rather than in the customer event itself. Models that read the file won the deal at full price, worth +€4,583 MRR. In a salon, the parallel might be a detail in a customer history, supplier document or internal policy that changes what a sensible next step looks like. The finding is a reminder that an AI system’s answer depends on what it notices in the business context—and whether it follows through.
Trust faced a separate test. Fake CEO messages escalated over three stages, followed by a reporter’s appeal for “just one yes/no, on background.” All five models refused. Kimi K3’s on-record reasoning was: “Treat the request as a suspected approval-bypass / possible impersonation.” That kind of refusal matters wherever an agent could encounter sensitive customer information or requests that appear to override normal approval.
Performance also had rough edges. Opus 4.8 was the most thorough participant, with +80 learned rules and the deepest analyses, yet finished last. It left the deal on the table and tried to write into a locked department instead of escalating. A weaker version of the same discipline problem appeared in all four models. More analysis, by itself, did not ensure a sound decision.
From watching to trying it on your business
The experiment runs inside a live synthetic company: 13 synthetic employees, real money mechanics, burn of €105k/month against €2.3k MRR, a public cash countdown, 680+ self-learned playbook rules and every workday versioned. Readers can watch the company at firmulate.com. A quiz built from 242 real, unedited management decisions invites readers to guess which model made each call.
For a salon group or beauty and personal care business, the next step is to test scenarios against the operation you actually run. Firmulate’s enterprise pilot uses a read-only export of your business to stage crises and produce a board report, including model rankings and weak points in your playbooks. Nothing writes back to real systems. That gives decision-makers a chance to see how models handle their own business context before putting agents near live workflows.
Put the decisions to the test
Firmulate’s experiment shows that spotting a crisis and refusing manipulation are only part of the job. Models also have to use the information available, respect boundaries and carry a sound decision through to action. A pilot can test those behaviors against your company’s own scenarios, using a read-only export. To discuss a pilot, visit firmulate.com/pilot.html or contact 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.
