Screenshot gallery
40+ screenshot-backed case studies of how shipped AI products handle UX—from ChatGPT, Claude, Gemini, Perplexity, and more.
44 items
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.
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.
Google GeminiOutput & Refinement
Gemini renders long-form output in-thread with inline source chips, comparison tables, section export, follow-up chips, refinement menus, Workspace handoffs, Maps split-pane, and a sources sidebar.
PerplexityPersonalization & memory
Perplexity personalizes search relevance: occupation and custom instructions, demographic modals, response length prefs, Health and Finance vertical profiles, and search-history memory with Brain upsell.
ManusAgent execution & deliverables
Manus agent runs: meeting minutes capture, working status with file edits, structured task completion, and slide preview modal.
ManusSignup & role segmentation
Manus onboarding: work-type role grid, Pro pricing with trial, task-ready home, credits popover, and feature announcement modals.
ManusTask composer & modes
Manus assignment bar: connector suggestions, + attach menu, skills, cloud computer, agent tiers, voice input, and mode-specific flows like Slides.
ClaudePersonalization & memory
Claude shapes behavior through natural-language profile instructions, opt-in chat memory under Capabilities, cross-platform memory import, and named voice style presets.
ChatGPTPersonalization & memory
ChatGPT separates AI behavior customization from technical settings. Users pick named tone presets, fine-tune characteristics, declare profile fields, and manage inferred memories with search, deprioritize, and version restore.
DeepSeekTool Switching in Composer
DeepSeek composer: Instant/Expert tier toggle, DeepThink and Search chips in the card, and attach with tier-specific limits.
Google AI ModeTool Switching in Composer
Google AI Mode on google.com: personalized greeting, + menu for attach and modes, AI Mode toggle, Lens, Canvas, and Create images.
LovableSignup & First-Run Onboarding
Lovable runs a four-step wizard for theme, name, role, and company size, then introduces connectors on first product visit.
LovableTool Switching in Composer
Lovable home composer: personalized greeting, + menu for attach and app-building tools, Build vs Plan modes, and inline voice dictation.
ChatGPTOutput & Refinement
ChatGPT renders structured answers in the thread with reasoning activity, version navigation, feedback, sharing, and selection-based refinement into writing blocks.
PerplexityCitations & Trust
Perplexity displays domain +N chips inline, a sources summary row, Links tab audit, Check sources on selections, and Wrong sources feedback.
PerplexityOutput & Refinement
Perplexity renders search answers with Answer/Links/Images tabs, research steps, follow-ups, export, rewrite, and selection refinement.
ClaudeArtifacts
Substantial work opens as an artifact card, then expands into a split pane with live preview, code view, and optional publish.
ClaudeOutput & Refinement
Claude keeps short answers in the message stream with per-message actions, non-destructive Try again, and version navigation.
PerplexityModel Selection Dropdown
Perplexity offers a comprehensive model switcher directly in the composer, displaying a wide array of AI models including GPT-5.2, Claude Opus 4.5, Gemini 3 Pro/Flash, Grok 4.1, and proprietary Sonar models.
PerplexityTool Switching in Composer
Perplexity allows users to select and activate different AI capabilities and modes directly from the composer interface.
ChatGPTDictation Mode
ChatGPT's dictation mode allows users to speak naturally and have their speech converted to text in real-time, enabling hands-free interaction with the AI.
ChatGPTTool Switching in Composer
ChatGPT allows users to select and activate different AI capabilities like Code Interpreter, DALL·E, and Web Search directly from the composer interface.
.webp)
ClaudeContext Chip Management
Claude allows users to attach files, images, and other context sources to conversations, displayed as removable chips.
ClaudeTool Switching in Composer
Claude allows users to select and activate different AI capabilities like Code Interpreter, Web Search, and file analysis directly from the composer interface.
.webp)
Google GeminiMultimodal Input
Gemini supports multiple input types including text, images, and files in a unified composer interface, allowing users to attach and interact with various content types simultaneously.
Google GeminiTool Switching in Composer
Gemini allows users to select and activate different AI capabilities and extensions like Google Workspace, YouTube, and Maps directly from the composer interface.
GoogleConversation Summaries in Spaces
Google Chat shows an AI-generated summary card for unread messages in Spaces so users can quickly catch up on the key topics.
ClaudeIncognito Mode
Claude offers an incognito (private) mode that lets users have conversations without saving them to history or using them to improve the model. The mode is toggled via a ghost icon in the header.
PerplexityShopping Tab & Instant Buy
Perplexity features a dedicated Shopping tab with a discovery feed of recommended products, displaying curated product cards with images, prices, ratings, and one-click purchase options.
ChatGPTImage Generation
ChatGPT's image generation feature allows users to create images using DALL·E directly within the conversation interface, with tool selection, prompt input, and result display integrated seamlessly.
ChatGPTResponse Refinement
ChatGPT provides a contextual menu on AI responses that allows users to refine or modify the output with specific instructions like "Try again", "Add details", "More concise", "Search the web", or "Think longer" without retyping their prompt.
GrokPersonalization
Grok provides personalization settings that allow users to customize their AI experience, including conversation preferences, response style, and contextual behavior settings.
Notion AIPrompt Starter Examples
Notion AI displays categorized prompt starter examples that help users discover AI capabilities and get started with common writing, editing, and content creation tasks directly within the editor.
ChatGPTSettings
ChatGPT presents settings through a centered modal interface with extensive controls for appearance, voice customization, data management, and parental controls, emphasizing both personalization and safety features.
ClaudeModel Switcher with Hierarchy
Claude implements a tiered model selection system that balances simplicity with power user needs. The main dropdown presents three current models with clear use-case descriptions, while a "More models" submenu provides access to legacy versions.
ClaudeSettings
Claude offers a comprehensive settings interface with a strong focus on AI personalization, allowing users to customize their profile, work context, personal preferences, appearance (including dyslexic-friendly fonts), and notification controls.
Google GeminiMode-Based Selection
Gemini reframes model selection as "mode" selection, presenting users with three performance tiers, Fast, Thinking, and Pro, each optimized for different task types and response complexity.
Google GeminiSettings
Gemini presents settings as a left sidebar menu with categories for activity tracking, personal context, connected apps, scheduling, theming, subscription management, and ecosystem integrations like NotebookLM.
GrokModel Selection
Grok offers intuitive model selection with Auto mode that intelligently chooses between Fast and Expert models, plus additional specialized models including Grok 4.1 Thinking, Heavy, and premium SuperGrok.
GrokMultimodal Input
Grok provides comprehensive multimodal input options through a paperclip menu, offering file upload, text content, sketching, cloud storage integration, and voice input capabilities.
GrokPersona Switcher
Grok offers project-based personas with specialized instructions and contextual prompts, including Legal Document Reviewer, Cover Letter Writer, Writing Assistant, Fitness Advice, Personal Finance Assistant, and the ability to create custom projects.
GrokTool Switching in Composer
Grok displays active tools as dismissible chips above the composer, allowing users to activate capabilities like DeepSearch and see them clearly indicated with the ability to remove them with an X button.
PerplexitySettings
Perplexity presents settings and help resources through a right-aligned dropdown menu that emphasizes onboarding, documentation, and support over traditional settings controls.