Word = spin synonyms. Sentence = shift tone. Paragraph = shorten or expand. That hierarchy — shown in a short video demo that reached roughly 712K views on August 31, 2026 — is the clearest articulation yet of micro-gesture AI writing UX: the model action follows how much text you selected, not whatever you typed into a side chat.
The demo reframes a debate explainx.ai keeps seeing across generative UI: should AI editing look like ChatGPT in a sidebar, or like direct manipulation — sliders, axes, and scoped transforms tied to selection? Comment threads on the post overwhelmingly argued for the second. That aligns with Runway Solaris's broader bet that gestures in, structured output out beats one omnibus prompt box for fine-grained work.
TL;DR
| Question | Answer |
|---|---|
| What's the core pattern? | Selection scope determines AI operation: word → synonyms, sentence → tone, paragraph → length |
| Why viral? | ~712K views — tangible alternative to "prompt the whole doc" |
| What do users want? | Tone sliders and axis controls, not chat re-prompting per edit |
| Relation to Solaris? | Same gesture-first philosophy applied to writing vs Interface World Model UI |
| Buildable today? | Partially via agent skills + editor selection APIs |
| Risk? | Unbounded "tone shift" without axes produces inconsistent voice across paragraphs |
The three-level grammar
Traditional AI writing tools often flatten everything to a single instruction channel: highlight text, open chat, describe the change. The viral demo instead encodes granularity as grammar:
| Selection | Operation | User mental model |
|---|---|---|
| Word | Spin synonyms | Thesaurus drag — local, reversible |
| Sentence | Shift tone (cold ↔ warm) | Emotional register dial, not rewrite-everything |
| Paragraph | Shorten / expand | Length transform with structure preserved |
That grammar matches how professional editors actually work: micro edits, meso tone passes, macro structure cuts. Chat-only UX forces macro prompts for micro problems — "make this word less corporate" becomes three sentences of instructions.
Why tone sliders beat chat for sentence-level work
Comment consensus on the thread: sliders communicate bounded change. A cold↔warm axis tells the model which dimension moves without re-stating genre, audience, and voice every time. That is the same design logic behind:
- DESIGN.md tokens — named axes instead of ad-hoc hex codes
- Ethan Mollick's spec-not-tricks prompting — constrain degrees of freedom
- Anti-slop skills like Garden — checklists before open-ended generation
Open-ended chat excels at discovery ("what tone should this be?"). Sliders excel at iteration once intent exists — the demo argues writing tools live mostly in iteration.
Parallel: Runway Solaris and "video is the universal interface"
Runway's August 31, 2026 Solaris launch — covered in depth on explainx.ai — frames chat and gestures as inputs to an Interface World Model that renders UI as live frames instead of HTML. Runway's pitch: "video is the universal interface."
The writing demo is not generating video UI, but the control philosophy rhymes:
| Solaris | Micro-gesture writing |
|---|---|
| Click/drag/type → next frame | Selection scope → edit class |
| Rejects code-as-intermediate for pixels | Rejects chat-as-intermediate for diction |
| Gestures carry structural intent | Selection carries structural intent |
Both push back on the default LLM product pattern — one textarea owns all semantics — in favor of channels matched to edit size.
For code-based generative UI — Antigravity artifacts, v0, Lovable — the analogous move is component-level controls (props, tokens) instead of "rewrite the page" prompts. Vercel's DESIGN.md drop is the spec-side version: give agents named axes before they paint pixels.
How to prototype this in your stack
1. Split operations into skills, not one mega-prompt
# word-spin/SKILL.md
When selection is a single word: propose 5 synonyms preserving POS and domain register.
# sentence-tone/SKILL.md
When selection is one sentence: shift tone along cold↔warm axis (0=clinical, 1=warm).
Preserve facts; change diction only.
# paragraph-length/SKILL.md
When selection is a paragraph: shorten 30% or expand 30% without adding new claims.
Install skills per explainx.ai's skills guide.
2. Pass structured params, not prose
Instead of: "Make this warmer but still professional"
Send: { "operation": "tone", "axis": "warmth", "value": 0.7, "text": "..." }
3. Frontend: slider + selection listener
Pair with DESIGN.md templates so the slider, selection highlight, and diff preview share one token file — avoids purple-gradient "AI app" slop.
Limits and open questions
- 712K views measures distribution, not product readiness — no shipped product name was attached to the demo in the viral post.
- Tone axes are culturally loaded; cold↔warm is a demo shorthand, not a universal model.
- Paragraph expand/shorten still needs factuality guards — same class of problem as LLM writing detection debates.
- Editor integration (Google Docs, Notion, VS Code) remains the hard engineering — UX pattern ≠ platform deal.
View counts and demo mechanics reflect the August 31, 2026 X thread; no independent product benchmark verified the editing quality.
Related reading
- Runway Solaris: Interface World Model without code
- Vercel DESIGN.md: spec-driven UI against AI slop
- DESIGN.md templates for agent-native UI
- What are Agent Skills? Complete guide
- Ethan Mollick: specs, not tricks
- Antigravity Interactive Generative UI Artifacts
- OpenDesign Harness beta: polished design generation