AI doesn't fail because the model is bad. It fails because there's nothing underneath it

There's a question every system runs into the moment it goes to production and starts doing real things: what exactly happened, in what order, against what data — and can you prove it? AI is just making that question very loud right now. Picture the case that gets more likely with every tool-using agent: a support agent — not a human, an LLM with tool access — cancels a subscription, issues a refund, fires off three follow-up emails. The next day the customer says: I never cancelled. Now answer...