QwenTool Switching in Composer
Qwen composer: calm default bar with multimodal studio in +, separate effort and voice products, Create Image and Web search as armed modes.
Empty home with Ask Qwen, Auto effort, mic, and waveform button; Qwen3.7-Plus in header.
What's happening
Qwen keeps a calm chat shell and hides the multimodal studio in +. Effort is separate from the chat model. Dictation stays in the bar; live Voice and Video leave for their own session.
Patterns
Progressive disclosure for generative, search, and deliverable jobs
Chat engines and image engines stay decoupled
Dictation vs realtime voice as separate products
UX Insights
- •Multimodal catalog lives in +, not home pills
- •Chat model, image engine, and effort need a map
- •Unlabeled twin voice controls invite mis-taps
- •Example cards that inject prompts teach generation
Design Decisions
Qwen splits text chat, image studio, and omni voice into one URL with nested modes instead of separate home surfaces.
More case studies
GLM (Z.ai)Tool Switching in Composer
GLM (Z.ai) composer: Magic Design, Full-Stack, and Write Code pills; Search vs Advanced Search; GLM-4.7 through 5.2; Deep Think Max; separate Agent home with Discord/Lark/WeChat.
KimiTool Switching in Composer
Kimi composer: agent pills that rewrite the bar into Websites, Docs, Sheets, Design, and Swarm; Instant/K3/K3 Swarm; + for files plugins skills and search; slash invoke.
ManusTask composer & modes
Manus assignment bar: connector suggestions, + attach menu, skills, cloud computer, agent tiers, voice input, and mode-specific flows like Slides.
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.