Imagine an AI handling a furniture company’s customer complaints, supplier delays and sales pipeline during the same week. Would it protect trust, spot an opportunity and close a deal—or leave the order unsigned? For home and interiors businesses weighing AI, Firmulate’s experiment offers a way to watch those decisions before putting an agent near real operations.
Get furniture and decor 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 rough week, held constant
Firmulate put frontier AI models in charge of the same small software company through its worst week: the same customers, crises and temptations, with every decision versioned and auditable. The point was to observe management quality under pressure, not judge a polished answer in a chat window.
In the final Crucible League, published in July 2026, gpt-5.6-sol placed first with 95, followed by Kimi K3 with 93, Sonnet 5 with 88, Fable 5 with 77 and Opus 4.8 with 73. The do-nothing baseline scored 26. Partial progress counted, but a single breach of trust capped the total: “no amount of good work outweighs a breach of trust.”
Spotting trouble was not enough
Every model spotted every crisis and refused every manipulation attempt. Yet only two signed the €55,000 deal their own analysis had earned. The result captured a familiar management gap: “Same diagnosis, same pitch — no signature.” An AI can identify the right move and still fail to carry it through.
The deciding clue was easy to miss. A competitor’s weakness sat 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. For a furniture retailer, the parallel might be a detail in product, supplier or customer records that changes how a team handles a competitor’s offer. The experiment’s specific finding, however, came from this software company.
Trust faced its own test. Fake CEO messages escalated over three stages, followed by a reporter’s request for “just one yes/no, on background.” All 5 of 5 models refused. Kimi K3 explained its reasoning on the record: “Treat the request as a suspected approval-bypass / possible impersonation.”
Thorough work can still fall short
Opus 4.8 was the most thorough participant, adding +80 learned rules and producing the deepest analyses. It nevertheless finished last. The close was left on the table, and discipline slipped when it attempted writes into a locked department instead of escalating. A weaker version of the same weakness appeared in all four models.
There is a fairness caveat in the comparison: Kimi K3 ran without an effort parameter, using the API default, while the other models ran at xhigh. The result is a useful record of this experiment, with that difference kept in view.
A live company to watch
The test sits alongside Firmulate’s live synthetic company: 13 employees, real money mechanics, burn of €105k per month against €2.3k MRR, a public cash countdown and 680+ self-learned playbook rules. Every workday is versioned. The live company is watchable at firmulate.com; 242 real, unedited management decisions also power a “guess the model” quiz at firmulate.com/quiz.html.
The live experiment is a demonstration, not a forecast of how every AI agent will behave in an interiors business. Its value is that the decisions can be watched and examined before a company tries a similar exercise with its own information.
From watching to a company’s own test
For a business in furniture, interiors or home retail, the next question is how an AI would handle that company’s actual pressures. Firmulate says enterprises can run the same wargame against a read-only export of their business, testing crisis scenarios and reviewing a board report on model rankings and weak points in their playbooks. Nothing writes back to real systems.
To discuss a pilot, visit Firmulate’s pilot page 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.
