CommerceCode sourceFree

Purchasing Concierge

Official Google codelab root agent that orchestrates burger and pizza sellers over A2A.

Pricing

Free

Commerce

Curated resource

Technical badges

Google ADKPython1.0-alpha

Marketplace signals

Views1.8K
Gets0
RatingNo ratings yet

What it does

Long-form description, mapped skills, and a concrete usage example.

Google's purchasing concierge codelab demonstrates a realistic multi-agent commerce flow where an ADK root agent acts as the A2A client and coordinates remote seller agents built on different frameworks. It is the clearest official example of cross-framework ordering through A2A.

Orchestrate seller agents

Decompose a user order and coordinate remote seller agents through A2A.

Maintain commerce dialogue

Keep context across seller interactions and confirmations during a purchase flow.

Example conversation

Input: "Show me burger and pizza menus, then order one spicy cajun burger and one BBQ chicken pizza." Output: the concierge routes requests to the seller agents, gathers confirmations, and completes the order.

Technical

Framework

Google ADK

Language

Python

Spec version

1.0-alpha

Interaction

Text

Supported input

TextJSON

Supported output

TextJSON

Requirements

API keys

Google AI

Infra

Python 3.11+

Estimated run cost

Cloud Run and Agent Engine cost plus model usage.

External services

Google Cloud Agent Engine, Cloud Run

How to install

Clone or access the repository at https://github.com/alphinside/purchasing-concierge-intro-a2a-codelab-starter.

Checkout the branch or tag `main`.

Prepare the required runtime: Python 3.11+.

Provision the required API keys: Google AI.

Connect the external services used by the agent: Google Cloud Agent Engine, Cloud Run.

Install dependencies, configure env vars, and deploy to your preferred host.

Follow the official Google codelab to deploy the purchasing concierge to Agent Engine and connect it to remote seller agents.

Ratings

No ratings yet

0 total ratings
Ratings appear here after buyers receive their secure feedback link.

Comments

Buyer discussion

0 total comments
No comments yet. The first useful buyer note can set the tone here.

Leave a comment

Sign in with GitHub or Google to comment on agents.

Purchased already? Use the secure link from your confirmation email to rate or report this agent. The public page stays open for browsing, but feedback actions require a verified buyer or downloader token.