Observed Signal · May 7, 2026 · Analysis · Source: UX Collective · Impact: 2/5 · Sentiment: Positive
AI Prompts Are Not Interfaces
Joshua Leigh argues that the dominant chat/text-prompt UI for contemporary AI is a regression to command-line style interaction that fails designers working on inherently visual or spatial tasks. The essay traces the history of graphical interaction (Sketchpad, Engelbart’s demo, Macintosh) and critiques text prompts for violating core interaction principles (visibility, reversibility, spatial manipulation). Leigh highlights emerging alternatives — canvas-driven interfaces (tldraw Make Real), embedded tools (Adobe Generative Fill, Photoshop), node-based editors (ComfyUI) and Figma Make — as early examples of multimodal, visual interfaces that let users show intent rather than describe it in text. The piece concludes that as models become multimodal, the interface layer must evolve from typing to direct visual manipulation.
Thoughtful analysis of AI UI design highlights practical limitations of text-prompt interfaces and points to emerging multimodal, canvas- and node-based tools; relevant to creative tooling and ad/marketing asset creation but not a platform policy or major product launch.
Track Figma Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Article titled "The prompt is not an interface" by Joshua Leigh was published on 2026-05-07 on UX Collective / Medium.
- The article cites historical interaction milestones: Ivan Sutherland’s Sketchpad (1963), Douglas Engelbart’s 1968 demo, and Apple’s Macintosh System 1 (1984).
- The text references multiple visual AI tooling examples: tldraw’s Make Real prototype, Figma Make (introduced 2025), ComfyUI (node-based editor), Adobe Generative Fill (Photoshop feature, 2023), and Runway.
- The author states LLMs are language-native models and that the chat/text prompt became the default UI because it was the fastest way to ship products around those models.
- The article argues that AI models are moving toward multimodality (image, audio, spatial understanding) and that text-only prompts are becoming a bottleneck for visual and spatial creative workflows.
Connected Companies & Entities
5 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Chat Box Shipped Fast — Not the Right UI
Adi Leviim argues that the ubiquitous AI chat box became the default interface because it was the fastest to ship with large language models, not because it is the best UX. The essay reviews decades of HCI patterns (direct manipulation, structured forms, progressive disclosure) lost to the chat-only surface and documents 2024 product retrofits from OpenAI, Anthropic and Google that reintroduced GUI surfaces (GPT Store, GPT-4o Voice, Artifacts, Projects, Canvas, Computer Use, Deep Research). Leviim distinguishes intent-based interaction from chat-based implementation and predicts the next phase of AI UX will be many small, scoped, structured surfaces (inline rephrase, highlight-to-rewrite, one-click variants) rather than general-purpose chat windows.
Prompt Won't Replace Drag & Drop
GoodBarber argues that AI prompt-based creation and traditional drag-and-drop interfaces are complementary rather than competitive. Drag-and-drop remains superior for precise, visible manipulations and for governing coherent design via components and a design system. Prompts excel at the long tail—singular, complex requests that would bloat a visual editor if represented with bespoke settings. The engineering challenge is integrating generated output into the product's existing design system and persistence so generated sections behave like handcrafted components. GoodBarber gives an example where an AI palette generator outputs colors that map into the platform's four-color semantic design system. The piece concludes that new abstraction rungs rest on prior ones and a good creation tool preserves multiple, shortest paths for different intents.
Prompt-Only Empty States Hurt AI Product Retention
Adi Leviim argues that modern AI products have replaced decades of empty-state UX design with a single centered prompt box and suggestion chips, which increases first-session drop-off. Drawing on A/B tests and anonymized analytics from a Chrome extension he co‑built, Leviim reports roughly 70% of new installs never return for a second session; versions that showed worked examples or pre-populated artifacts materially outperformed blank-prompt variants. The essay traces this failure to abandoned HCI principles (signifiers, recognition over recall, scaffolding) and recommends four properties for a deliberately designed AI empty state: show a worked example, offer a starting verb, expose model limits, and enable action before the first prompt. The author discloses commercial interest in extensions that fill AI UX gaps.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.