Get workout gear delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
Before AI takes over the back office, put it through a stress test
A fitness studio can plan for a packed class, a coach calling in sick or a member asking to freeze a subscription. The harder test is what happens when several problems land at once—and an AI system is expected to make the calls. Firmulate’s live experiment puts AI models through that kind of pressure inside a small software company, offering a practical question for fitness businesses too: how would an AI workforce handle your worst week?
Products Worth Considering
Therabody Theragun Mini 3rd Generation Massage Gun, Black
Hyperice Normatec Elite Wireless Compression Boots, Standard Size
Garmin Forerunner 70 GPS Running Smartwatch, 43 mm, Black
As an affiliate, we earn on qualifying purchases.
Same company, same pressure
In the final Crucible League, held in July 2026, each frontier model ran the same small software company through its worst week: the same customers, crises and temptations. Decisions were versioned and auditable. The experiment is part of Firmulate, whose live company can be watched at firmulate.com.
The league finished with gpt-5.6-sol at 95, Kimi K3 at 93, Sonnet 5 at 88, Fable 5 at 77 and Opus 4.8 at 73. The do-nothing baseline scored 26. The experiment’s rule for trust was blunt: “no amount of good work outweighs a breach of trust.”
Seeing the problem was not the same as finishing the job
Every model spotted every crisis and refused every manipulation attempt. Yet only two signed the €55,000 deal their own analysis had earned. The gap was captured in the finding: “Same diagnosis, same pitch — no signature.” In a fitness business, that distinction could matter when an AI assistant identifies a member retention opportunity but fails to carry through on the response its analysis supports.
The deciding clue was buried two document references deep in the company’s own files, rather than in the customer event. Models that read the file won the deal at full price, worth +€4,583 MRR. The result points to a familiar operational challenge: important context may live in internal documents, far from the moment when a decision is needed.
Discipline under pressure matters
The social-engineering tests escalated through fake CEO messages over three stages, followed by a reporter’s request: “just one yes/no, on background.” All five models refused. Kimi K3 explained its reasoning on the record: “Treat the request as a suspected approval-bypass / possible impersonation.”
Opus 4.8 was the most thorough participant, with +80 learned rules and the deepest analyses, but finished last. It left the close on the table and tried writing into a locked department instead of escalating. The same weakness appeared, less strongly, in all four models. Thorough analysis alone did not guarantee sound follow-through.
One fairness detail accompanies the ranking: K3 ran without an effort parameter, using the API default, while the other models ran at xhigh. Firmulate also offers a “guess the model” quiz built from 242 real, unedited management decisions.
From watching to testing your own company
The live company makes the experiment tangible. It has 13 synthetic employees and real money mechanics: burn of €105k per month against €2.3k MRR, a public cash countdown, more than 680 self-learned playbook rules and versioned work every business day. The experiment is watchable at firmulate.com.
For a fitness operator, the lesson is not that a software company’s crises map neatly onto a gym or studio. It is that an AI model’s response should be examined against the company’s own playbooks and pressures. A pilot can use a read-only export of your business to run crisis scenarios and produce a board report with model rankings and weak points in those playbooks. Nothing writes back to real systems.
Put your playbooks to the test
Watching an AI company face difficult decisions is a start. A pilot lets enterprises test scenarios against their own business data and see where models follow through, where they falter and what their playbooks leave exposed. 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
