ProductsOfficial

Milestone: Gemini introduces on-demand generative interfaces

Google announced visual layout and dynamic view experiments alongside Gemini 3.

Event 2025-11-18Source published 2025-11-18Indexed 2026-10-10Verified 2026-10-10

Why it matters

Responses can adapt both their layout and interaction to a question.

A closer look

Visual layout assembles rich modules. Dynamic view generates a custom interface through coding.

Who this is for

Developers, designers and product teams

Original sources

Google ↗blog.google

Revisions & corrections (1)

2026-10-10 — Initial source-verified editorial collection

Related events

Products2026-10-27

OpenDuet combines proactive attention, persistent tasks and action approval in an open-source AG‑UI workspace

On October 27, CopilotKit released OpenDuet, a self-hostable single-owner proactive-agent template that connects any compatible agent through AG‑UI. Across web, mobile, Slack and Teams, it triages what needs attention, prepares a morning brief, continues background work, and presents an action for approval before sending, paying, signing or deleting.

CopilotKit official announcement and OpenDuet repositoryOfficial

Products2026-10-22

CopilotKit launches Soar, self-hosted enterprise AI coworkers built on AG-UI

CopilotKit announced Soar early access on October 22: engineers deploy it on customer infrastructure, AG-UI connects agents to web, desktop, Slack, Teams, text and internal tools, and a shared checkpoint governs sensitive actions.

CopilotKitOfficial

Products2026-10-22

OpenAI makes the Decisions API generally available for low-latency UI branching

OpenAI made the Decisions API generally available on October 22. Powered by GPT-6 Luna, it returns a probability, choice or score from text, images or structured input, and can drive live UI state such as avatar expressions through GPT-Live decision.event messages.

OpenAIOfficial