01Hub di professionisti · Generative UI
Costruiamo Interfacce AI Che vanno in produzione.
Consulenza e sviluppo di Generative UI per team che hanno bisogno di funzionalità AI in produzione — non demo. Streaming components, flussi di tool-use, workflow agentici, consegna end-to-end.
02Principi
What is generative UI?
Generative UI is interfaces produced by language models at runtime. Components are streamed from LLM output and rendered as real UI, not text. The model picks the form alongside the content: a chart for numbers, a form for input, a list for choices.
Il modello sceglie la forma
Un grafico per i numeri, un modulo per l'input, un elenco per le scelte.
Componenti dalla tua libreria
Il modello non scrive HTML o JSX — sceglie dalla tua libreria.
Streaming, non testo
Gli elementi interattivi arrivano in streaming come vera UI, non come testo.
Modifiche tramite prompt
I cambiamenti si pubblicano modificando il prompt o il catalogo.
Traditional UI
Generative UI
Form chosen by the designer at build time
Form chosen by the model at inference time
Static templates, deterministic outcomes
Runtime components, probabilistic outcomes
Same screen for every user, every request
Different shape per user, per request
Changes ship through a release cycle
Changes ship by editing the prompt or the catalog
03Novità
Latest
What we published most recently.
Cos'è la Generative UI? La guida completa
Tutto quello che devi sapere sui sistemi AI che generano componenti UI interattivi, non solo testo.Generative UI vs UI tradizionale: differenze chiave
Come le interfacce generative differiscono dalle UI convenzionali e quando ogni approccio ha senso.Costruisci la tua prima Generative UI con Vercel AI SDK
Guida passo dopo passo per creare la tua prima interfaccia AI con streaming components.04Guida pratica
Field guide
Six tracks across the generative-UI landscape. Pick by where you are — engineer mid-build, designer mapping patterns, PM evaluating, or executive sizing the bet.
Runtimes & SDKs
Vercel AI SDK, CopilotKit, Tambo, Thesys C1, A2UI — how each one streams components, where the seams are, and what production looks like.
Patterns & components
Interaction patterns for LLM-rendered UI — disclosure, repair flows, tool confirmations, and the design questions GenUI raises.
Designers · EngineersProduction engineering
Observability, performance, testing, accessibility. What it takes to put a streaming, LLM-rendered interface in front of users and keep it up.
EngineersRAG & tool use
Retrieval-augmented generation, tool calling, agent workflows. Patterns that move generative UI past static catalogs into real action.
EngineersState of the field
Market state, vendor landscape, adoption curves. What is and isn't shipping in production right now — for evaluation, scoping, and bets.
PMs · Executives · ConsultantsGetting started
What generative UI is, who it's for, when it makes sense to adopt. The entry-level primer for anyone new to the term.
Written for engineers, designers, product managers, and executives working on or evaluating generative UI. Topic-organised navigation and per-role filters are on the roadmap.
05Stato
State of generative UI — runtimes at a glance
Five production-grade options, compared on stack, streaming model, openness, and maturity.
| Runtime | Maturazione | In breve |
|---|---|---|
| Vercel AI SDK | Mature | Streaming React/Vue components with first-class tool use. The default for new Next.js and Nuxt apps. |
| CopilotKit | Maturing | Drop-in copilot hooks and UI primitives. Strong for adding an assistant to an existing app. |
| Tambo | Early | Component catalog the model picks from. Useful when the design system is the unit of generation. |
| Thesys C1 | Maturing | Hosted API that returns ready-to-render UI. Trades infra ownership for time-to-first-screen. |
| A2UI (Google) | Early | Open JSON schema for renderer-agnostic UI from agents. Cross-runtime, very early. |
Open Source
Markdown in streaming senza sfarfallio
I renderer basati su innerHTML distruggono il DOM a ogni token, causando sfarfallio, perdita del focus e reflow del layout. Generative DOM confronta l'AST e aggiorna solo ciò che è cambiato: fino a 90× meno lavoro sul DOM, senza sfarfallio.
usermostra vendite Q1
modeltool · revenueChart({range:"Q1",currency:"RUB"})
dom<RevenueChart/> — montato
dom<FilterPanel/> — montato
diffsolo i nodi modificati · senza sfarfallio
07Open Source
Web component che gli LLM possono davvero comporre
Oltre 100 tag indipendenti dal framework — superfici di chat, grafici, matrici decisionali, widget didattici — ciascuno con un meta.json validato che espone props, eventi, slot, temi e dipendenze come JSON leggibile dalla macchina. Il modello vede il catalogo come uno sviluppatore e sceglie la primitiva giusta per i dati che sta per renderizzare.
Catalogo: 100+ tag · meta.json su ciascuno.