json-render/chat: Generative UI for Slack and Microsoft Teams

X postChris TateAnnouncement

Chris Tate announced json-render/chat, a library enabling generative user interfaces across enterprise chat apps such as Slack and Microsoft Teams. AI agents can reply with native cards containing tables, charts, fields, and buttons. UI components stream in real time using a unified catalogue across Chat SDK platforms.

Key points

  1. Enables AI agents to reply with native cards containing tables, fields, charts, and buttons.
  2. Streams components in real time as the underlying language model writes output.
  3. Provides a single component catalogue across all Chat SDK platforms.
  4. Designed to integrate directly with Vercel's Chat SDK and AI SDK workflows.
  5. Targets Slack, Microsoft Teams, and other chat messaging ecosystems.

Why it matters

Building interactive bot messages for Slack and Teams previously required maintaining distinct platform schemas such as Block Kit and Adaptive Cards. A unified generative UI catalogue standardises and accelerates agent development.

Analysis

Generative UI beyond the Web

With @json-render/chat, developer Chris Tate brings generative UI mechanics to third-party team chat platforms. While generative UI has gained significant traction inside dedicated web apps via component-streaming libraries, enterprise chat platforms have remained siloed behind bespoke layout formats—such as Slack's Block Kit and Microsoft's Adaptive Cards.

Architecture and Workflow

The library coordinates with Vercel's Chat SDK and AI SDK ecosystem:

  • Unified Catalogues: Developers define standard components once (e.g., using defineCatalog from json-render/core) instead of tailoring JSON specs for each chat provider.
  • Streaming Cards: UI widgets render progressively as tokens stream from the model.
  • Rich Components: The system natively supports tables, metric fields, charts, and actionable controls such as download or action buttons.

While the announcement highlights cross-platform compatibility, operational details—such as handling button events while a card is still actively streaming—depend on underlying client constraints.

Original post

Chris Tate

@ctatedev · 7 November 2026

Introducing @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚌𝚑𝚊𝚝 Generative UI for Slack, Teams and more → Agents reply with native cards → Tables, fields, charts and buttons → Streams in as the model writes → One catalog for every Chat SDK platform t.co/QfZG22QBN7

4.2k likes111 replies5.1k bookmarks240.4k views

View on X
Selected replies (5)
  • @utpalnadiger @ctatedev really really cool checking it out rn! t.co/OQ76mCvZhv
  • @utpalnadiger @JackRNewhouse @ctatedev lfg. it's live for us. random sample data below. t.co/FmtQasGGgI
  • @rabi_guha @siscia_ @ctatedev @openuidev Fwiw i think competition is healthy here. Still very early days for Generative UI and this keeps us on our toes We've supported this for quite a while now via our community plugins but I guess time to make it official 🙂
  • @petrusenko_max @ctatedev with one catalog, does slack render block kit and teams adaptive cards, or does the shared shape win everywhere?
  • @balaSivagnanam @ctatedev Works with block kit? Major pain with that is to create the components dynamically in that doesn’t break the rendering with block kit.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 8 November 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:Chris Tate

    Stream Generative UI in Chat SDK Agents Using json-render

    Vercel has added json-render support to its Chat SDK, enabling agents to stream generative UI directly into chat platforms. A typed component catalogue converts JSON specs into native Block Kit or Adaptive Cards messages. This simplifies delivering structured, interactive UI from AI bots.

    AI & LLMs· Announcement

  • X post:Guillermo Rauch

    Generative UI in Slack and Teams via AI SDK, Chat SDK, and json-render

    Vercel has introduced generative UI streaming for Chat SDK agents using json-render. Language models output typed JSON specifications that convert directly into native UI cards for platforms like Slack and Microsoft Teams. Guillermo Rauch predicts this approach will become the dominant paradigm for Human-Agent Interaction.

    2.6kbookmarks163kviews

    AI & LLMs· Announcement

  • Repository:CopilotKit/OpenTag

    OpenTag: Self-Hosted AI Agent for Slack and Microsoft Teams

    OpenTag is an open-source starter application by CopilotKit that connects LangGraph- and AG-UI-based AI agents directly into Slack and Microsoft Teams for triage and knowledge work.

    1.2kstarsTypeScript

    AI & LLMs· Tool

  • Repository:vercel/ai

    Vercel AI SDK: Provider-Agnostic TypeScript Toolkit for AI Applications and Agents

    Vercel's AI SDK is an open-source TypeScript library for developing AI-powered applications and agents. It provides a unified API across diverse model providers including OpenAI, Anthropic, and Google, and integrates directly with frameworks such as Next.js, React, Svelte, Vue, and Angular.

    26.6kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.