01Centro de profesionales · Generative UI
Construimos Interfaces AI Que se despliegan.
Consultoría y desarrollo de Generative UI para equipos que necesitan funcionalidades AI en producción — no demos. Streaming components, flujos de tool-use, workflows de agentes, entrega end-to-end.
02Principios
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.
El modelo elige la forma
Un gráfico para los números, un formulario para la entrada, una lista para las opciones.
Componentes de tu biblioteca
El modelo no escribe HTML ni JSX — elige de tu biblioteca.
Streaming, no texto
Los elementos interactivos se transmiten como UI real, no como texto.
Cambios a través del prompt
Los cambios se despliegan editando el prompt o el catálogo.
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
03Novedades
Latest
What we published most recently.
¿Qué es Generative UI? La guía completa
Todo lo que necesitas saber sobre los sistemas AI que generan componentes de interfaz interactivos, no solo texto.Generative UI vs UI tradicional: diferencias clave
Cómo las interfaces generativas se diferencian de las UIs convencionales y cuándo tiene sentido cada enfoque.Construye tu primera Generative UI con Vercel AI SDK
Guía paso a paso para crear tu primera interfaz con AI y streaming components.04Guía de campo
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.
05Estado
State of generative UI — runtimes at a glance
Five production-grade options, compared on stack, streaming model, openness, and maturity.
| Runtime | Madurez | Resumen |
|---|---|---|
| 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. |
Código abierto
Markdown en streaming sin parpadeos
Los renderizadores basados en innerHTML destruyen el DOM en cada token, provocando parpadeos, pérdida de foco y saltos de layout. Generative DOM compara el AST y actualiza solo lo que cambió: hasta 90× menos trabajo en el DOM, sin parpadeos.
usermuestra ventas Q1
modeltool · revenueChart({range:"Q1",currency:"RUB"})
dom<RevenueChart/> — montado
dom<FilterPanel/> — montado
diffsolo nodos modificados · sin parpadeo
07Código abierto
Componentes web que los LLM pueden componer de verdad
Más de 100 tags agnósticos del framework — superficies de chat, gráficos, matrices de decisión, widgets de lecciones — cada uno con un meta.json validado que expone props, eventos, slots, temas y dependencias como JSON legible por máquina. El modelo ve el catálogo igual que un desarrollador y elige la primitiva adecuada para los datos que va a renderizar.
Catálogo: más de 100 etiquetas · meta.json en cada una.