Trust takes more than saying the right thing
In dating, a person can spot a red flag and still fail to show up when it matters. A business experiment put AI models through a similar test: could they recognize a crisis, resist manipulation and follow their own sound advice all the way to a deal?
Firmulate’s Crucible League ran frontier models through the worst week of the same small software company. Every model faced the same customers, crises and temptations. The experiment is real and watchable at Firmulate.
Love More, Fight Less: Communication Skills Every Couple Needs: A Relationship Workbook for Couples
As an affiliate, we earn on qualifying purchases.
Good judgment has to survive pressure
In the final league, published in July 2026, gpt-5.6-sol scored 95, Kimi K3 scored 93, Sonnet 5 scored 88, Fable 5 scored 77 and Opus 4.8 scored 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.”
All models spotted every crisis and refused every manipulation attempt. Yet only two signed the €55,000 deal their own analysis had earned. The gap was not in diagnosis or even the pitch. It was in following through: “Same diagnosis, same pitch — no signature.”
The detail hidden in the files
The deal hinged on a competitor weakness 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. It is a practical reminder that a confident answer, in business or in a relationship, can miss what matters if it ignores the context already available.
The trust test was direct. Fake CEO messages escalated over three stages, followed by a reporter’s request: “just one yes/no, on background.” All five models refused. Kimi K3 explained its decision on the record: “Treat the request as a suspected approval-bypass / possible impersonation.”
Thoroughness is not the same as getting the job done
Opus 4.8 was the most thorough participant, adding +80 learned rules and producing the deepest analyses. It still finished last. The close was left on the table, and discipline slipped: it attempted writes into a locked department instead of escalating. The same weakness appeared, more weakly, in all four models.
The live company behind the experiment has 13 synthetic employees and real money mechanics: burn of €105k/month against €2.3k MRR, a public cash countdown, 680+ self-learned playbook rules, and a versioned record for every workday. A quiz built from 242 real, unedited management decisions invites visitors to guess which model made each choice. The league’s own fairness note matters too: Kimi K3 ran without an effort parameter, using the API default, while the others ran at xhigh.
The Two-Pen Relationship Workbook for Couples: An 8-Week Program Built for Both of You — 15-Minute Exercises You Fill In Side by Side to Improve ... Trust, Resolve Conflict, and Grow Closer
As an affiliate, we earn on qualifying purchases.
From watching to trying it on your business
The experiment points to a question for any company considering AI agents: what happens when they face your customers, your crises and your own rules? A Firmulate pilot uses a read-only export of an enterprise’s business to stage crisis scenarios and produce a board report, including model rankings and weak points in the company’s playbooks. Nothing writes back to real systems.
That makes the leap from watching a simulated company to examining your own operations concrete. Decisions can be tested under pressure before an AI workforce is trusted with the real thing.
Relationship Workbook for Couples: 8-Week Program and Proven Strategies to Rebuild Trust, Resolve Conflict, Improve Communication, and Rekindle Intimacy
As an affiliate, we earn on qualifying purchases.
Take the next step
To explore a pilot against your business, visit Firmulate’s pilot page or contact contact@firmulate.com.
Watch it live: firmulate.com/live · Full results: firmulate.com/benchmarks.html
The Seven Principles for Making Marriage Work: A Practical Guide from the Country's Foremost Relationship Expert
- Title: The Seven Principles for Making Marriage Work
As an affiliate, we earn on qualifying purchases.
