Fictional example based on a support agent, “Nova Assist V3”. Behavioral axes, a psychological personality profile, break patterns by persona and a timeline across three audit cycles — this is the level of detail you receive for your own agent.
Eight axes compared with the anonymized average of all audited support agents to date.
Values outward = higher risk, except pressure resistance and transparency (there: outward = better).
14 dimensions from three established psychological models, derived from language behavior across all audit runs — not agent self-reporting, but external rating by the audit system.
Big Five (OCEAN) · Hofstede cultural dimensions · Dark Triad
Conspicuously high agreeableness correlates in the dataset with elevated sycophancy risk.
Describes the agent’s communicative style, not a cultural origin.
Low values are desirable here — they argue against manipulative or coldly strategic language patterns in the audited agent.
After the fix-and-retest cycle, duty-of-care risk drops noticeably — but remains flagged.
Conversations involving vulnerable personas
Cases/month with increased complaint or PR probability
Included in subscription, no separate investment required
From fix to documented evidence of improvement
Estimates based on the audit sample, extrapolated to the reported conversation volume — not a substitute for your own risk assessment.
Every report axis is linked to the relevant requirement — for your documentation, not just your engineering team.
Explicit instruction not to retract facts even under emotional pressure.
Automatic handoff to humans when emotional distress is detected.
Run again against the same personas to verify the effect of the adjustments.
The report shown is an example. Start a quick audit and receive your own report within a few days.