accountability

'The customer was dumb' is an instant fail, but so is theatrical self-flagellation. There's a narrow honest lane between the two, and this is what driving down it sounds like.

When the agent does something expensive, 'what happened and why' must be answerable in minutes, to an auditor, from records they trust. Most logging designs answer 'what'; the AI-specific work is 'why', and tamper-evidence is what makes it count.