ChatGPTHuman in the Loop
ChatGPT clarifies before acting: structured questions for bookings, email draft cards with edit/export handoffs, and explicit limits when it cannot complete an action.
Restaurant booking: limits stated, then clarifying questions for party size, time, and cuisine
What's happening
ChatGPT gates consequential work behind clarification, editable draft cards, and explicit export handoffs — never implying an action completed when the user still owns the final step.
Patterns
Clarifying questions, draft cards, and handoff to user mail apps or reservation sites
UX Insights
- •Capability boundaries appear in the first sentence, not after a failed attempt
- •Bulleted clarifying questions reduce back-and-forth
- •Email drafts use card UI with Edit and export-to-mail-app instead of auto-send
- •Rich recommendations make booking handoffs feel useful rather than abrupt
Design Decisions
Rather than simulating agency, ChatGPT separates research from execution and keeps the user in control of consequential bookings.
More case studies
Google GeminiHuman in the Loop
Gemini asks clarifying questions before drafting email, previews Gmail drafts in a card, and gates Send behind explicit user approval.
PerplexityHuman in the Loop
Perplexity surfaces Gmail and Outlook connector chips in the composer and lets users Allow or Disable individual read and write tools.