{
  "id": 18511089,
  "title": "Yelp Combines Native and Server-Driven UI for Its AI Assistant",
  "url": "https://urgent.news/2026/11/06/yelp-combines-native-and-server-driven-ui-for-its-ai-assistant",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-06T14:25:00.000Z",
  "source": {
    "name": "InfoQ",
    "slug": "infoq",
    "url": "https://www.infoq.com/news/2026/11/yelp-assistant-hybrid-ui/"
  },
  "original_language": "en",
  "account": "Yelp has integrated a hybrid user interface for its AI Assistant, merging native mobile elements with server-rendered conversation display. This hybrid method, built on Yelp's CHAOS framework, enables rapid UI adjustments across platforms. CHAOS, an acronym for Content Hosting Architecture with Optimization Strategies, centralizes conversation content rendering while preserving native navigation and input functionality. Yelp Assistant debuted on iOS in 2024, assisting users in generating requests for local service professionals, and has since broadened to manage inquiries about businesses and facilitate actions like reservations and food orders. CHAOS supports web, iOS, and Android interfaces. Daniel Andrade Groppe, Services Tech Lead at Yelp, explained that CHAOS lacked certain features needed for the Assistant, such as text input fields and network requests. Consequently, Yelp opted for a hybrid approach, retaining native navigation and message input while employing CHAOS to render the conversation section. The UI architecture separates view configuration from conversation data, allowing a chat to initiate by fetching the CHAOS configuration and initializing a dataset for message events. Subsequent events update the existing view without re-fetching the configuration, with events encompassing persistent user and bot messages, temporary typing indicators, quick replies, and links to external destinations. The backend can also transmit actions to manipulate the UI, such as sending messages, links, and disabling chat input upon task completion. This event-driven design decouples rendering from conversation logic, enabling teams to update presentation without necessitating a new client release. Yelp's implementation extends this model to a conversational interface while maintaining native controls and client-side management of message state and interactions. While the architecture introduces coordination challenges and necessitates learning both the Assistant and CHAOS, it also facilitates independent feature development and enables the reuse of Android Assistant for the Biz Ask Anything pilot. This work has established the groundwork for Yelp's next-generation Assistant, which integrates business information with actionable features.",
  "summary": "Yelp combines native mobile controls with server-driven conversation rendering in its AI Assistant using the CHAOS framework. The architecture separates view configuration from conversation data, supports backend-driven chat interactions, and enables faster UI updates without new app releases. Yelp also discusses cross-platform challenges and reuse for its Biz Ask Anything pilot. By Leela Kumili",
  "key_points": [
    "Yelp combines native UI with server-rendered conversation for AI Assistant",
    "CHAOS framework powers hybrid UI across iOS, web, Android",
    "Event-driven design decouples rendering from conversation logic"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}