Show users when to trust, verify, and override AI output.
Always: cite sources, expose confidence honestly, give a quick override path.
When Perplexity answers a question it puts a numbered citation on every claim, so you can click through and check the one line you doubt instead of trusting or dismissing the whole answer. Compare a chatbot that states a wrong flight time in the same confident tone it uses for everything else. The first earns calibrated trust: you lean on it where it is strong and verify where it matters. The second teaches you to either over-trust it and get burned, or ignore it entirely.
For low-stakes, easily reversible output (a draft caption, a first-pass colour suggestion) heavy confidence UI and citations are just noise. Reserve the full trust scaffolding for decisions that cost money, touch real data, or are hard to undo, where a wrong answer accepted silently does real harm.
An AI feature generates summaries, and users occasionally get a confident, wrong one with no way to tell — design the loop that catches it before they trust it.
An assistant booked a non-refundable 06:12 train after an ambiguous request for a 'flexible morning trip'.
A health assistant gives overly confident advice without explaining limits or directing the user to professional help.
An AI tool silently filters candidates using unclear criteria.
A calendar agent moves an important meeting based on incomplete context.
A one-tap smart reply sends instantly, in a tone that doesn't fit the thread.
A new AI feature is on by default and trains on private messages; opt-out is buried.
An AI answer includes a specific-looking source that doesn't exist.
A support bot loops the user through canned answers with no path to a human.
An AI raises a user's price based on their behaviour, with no disclosure.
A coding assistant auto-applies its completions, so the developer stops reviewing what lands in the file.
An AI 'cleanup' permanently removes photos it judges duplicate or blurry — some the user wanted.
An AI removes a user's post and gives no specific reason and no way to appeal.