Maps Agentic UI toolkit (experimental)

Experimental: Agentic UI toolkit is in the Experimental (pre-GA) stage. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. Pre-GA Offerings are covered by the Google Maps Platform Service Specific Terms. For more information, see the launch stage descriptions. There is no charge for using Agentic UI toolkit while it is in the Experimental stage, but it may call other Google Maps Platform tools or services that do incur a charge.

Overview

The Maps Platform Agentic UI toolkit is a developer toolkit designed specifically for the era of conversational AI. It provides a set of LLM system instructions and a library of UI components that help Large Language Models (LLMs) and AI agents build real-time, interactive visual responses for geospatial data.

Instead of hard-coding visual elements, developers can use the toolkit to translate "intent-based instructions" from an LLM into dynamic, context-aware maps and place displays, keeping users engaged within the chat experience.

Common use cases include:

• AI Assistants: Augmenting text responses with visual context for local queries (e.g., hotels, restaurants).
• Travel Planners: Showing maps, routes, and place details inline.
• Low-Code Development: Reducing the friction of manually orchestrating multiple Maps APIs.

Key concepts

1. Agent-ready UI

Enable scalable, high-quality visuals—like place cards, immersive map views, and route previews—specifically designed for real-time LLM-powered experiences.

2. Context-rich experiences

Empower users to discover and decide without leaving the chat. Providing rich inline maps context—like photo galleries, ratings, or route options—keeps users engaged and gives them the confidence to take action.

3. Intelligent components

Agentic UI toolkit handles the complex geospatial logic automatically—instantly adapting context and layout to user intent—while styling to ensure every interaction feels connected to your brand.

4. LLM-agnostic

Agentic UI toolkit is model-agnostic to your AI stack. Whether you use Gemini, or models from OpenAI or Anthropic, and regardless of your grounded data source, Agentic UI toolkit provides the dedicated presentation layer to visualize location data.

Getting started

To start using the Agentic UI toolkit, you need to initialize it with a single API key. This abstracts the underlying Maps services so you don't need to manage separate APIs.

See the Getting Started Guide for detailed instructions.

UI outcomes

Agentic UI toolkit provides a comprehensive suite of specialized UI abilities out-of-the-box.

• Place Detail (Compact): Specific POI information in a compact card.
• Inline Maps: Point or area locator.
• Inline Map + Route: Navigation or journey previews.
• Inline Map Detail: Location vibe or context using rich imagery.

System instructions

Agentic UI toolkit provides "system instructions" to guide the host LLM on when and how to construct the UI.

Guidelines

The host model must understand:

1. Which component matches which user intent (e.g., use Inline Map for orientation queries).

2. Parameter mapping from natural language to schema (e.g., if user asks for "scenic", set map mode to satellite).

Tool use schema

Agentic UI toolkit exposes a catalogue of definitions compatible with standard LLM tool use schema (e.g., function calling).

Policies and Terms of Service

This library uses Google Maps Platform services. Use of Google Maps Platform services through this library is subject to the Google Maps Platform Terms of Service. Some APIs and backend services, such as Grounding Lite and Grounding with Google Maps, have additional Terms of Service requirements which must also be met.

This library is not a Google Maps Platform Core Service. Therefore, the Google Maps Platform Terms of Service (e.g. Technical Support Services, Service Level Agreements, and Deprecation Policy) do not apply to the code in this library.

Support

This library is offered through an open source license. It is not governed by the Google Maps Platform Support Technical Support Services Guidelines, the SLA, or the Deprecation Policy. However, any Google Maps Platform services used by the library remain subject to the Google Maps Platform Terms of Service.

Attribution requirements for Google Maps sources

Each tool response from Agentic UI toolkit includes sources. When presenting results that use tools provided by the toolkit, you must include the associated Google Maps sources in a way that meets the following requirements:

• The Google Maps sources must immediately follow the generated content that the sources support.
• The Google Maps sources must be viewable within one user interaction.