Uncertainty Communication
No product differentiates a knowledge gap from a principled limit. Hedging language appears mid-response where users who skim miss it entirely.
Problem
Every AI response carries uncertainty. Five of six products communicate it exclusively through language — no visual differentiation. Hedging language is often placed mid-response, meaning users who skim encounter confident claims without their caveats. No product distinguishes between 'I don't know' and 'I can't know.'
Prescription
Epistemic banners appear before the response body, not within it. Three distinct states: knowledge gap (amber — model searched proactively), principled limit (red — structural boundary), probabilistic (blue — claim-level uncertainty via dotted underlines with hover explanations).
Design decisions
Banner threshold determines when uncertainty is surfaced — not every response warrants one. Proactive web search on knowledge gaps matches observed behavior in Claude and Perplexity. Claim-level underlines require the model to surface confidence at the assertion level.
Tradeoffs
Prominent epistemic banners on every uncertain response risk alert fatigue. Visual confidence indicators imply model self-knowledge that may not be reliable — underlines are more honest than scores. Hover tooltips add interaction cost for users who want a direct answer.
Pattern definition
Problem
Every AI response carries uncertainty. Five of six products communicate it exclusively through language — no visual differentiation. Hedging language is often placed mid-response, meaning users who skim encounter confident claims without their caveats. No product distinguishes between 'I don't know' and 'I can't know.'
Prescription
Epistemic banners appear before the response body, not within it. Three distinct states: knowledge gap (amber — model searched proactively), principled limit (red — structural boundary), probabilistic (blue — claim-level uncertainty via dotted underlines with hover explanations).
Design decisions
Banner threshold determines when uncertainty is surfaced — not every response warrants one. Proactive web search on knowledge gaps matches observed behavior in Claude and Perplexity. Claim-level underlines require the model to surface confidence at the assertion level.
Tradeoffs
Prominent epistemic banners on every uncertain response risk alert fatigue. Visual confidence indicators imply model self-knowledge that may not be reliable — underlines are more honest than scores. Hover tooltips add interaction cost for users who want a direct answer.
Interactive demo
Audit finding
Five of six products communicate uncertainty exclusively through language — no visual differentiation between high-confidence and uncertain claims. Hedging language was observed mid-response in both Claude and ChatGPT, meaning users who skim encounter confident assertions without their caveats. No product in the audit distinguishes between a knowledge gap and a principled limit — they look identical in every interface.
All states