CommerceCode sourceFree

Expense Reimbursement Agent

Official Google ADK sample for expense reimbursement with multi-turn input collection and webforms.

Pricing

Free

Commerce

Curated resource

Technical badges

Google ADKPython1.0-alpha

Marketplace signals

Views1.3K
Gets0
RatingNo ratings yet

What it does

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

This official Google sample uses ADK to expose an expense reimbursement workflow as an A2A server. It accepts text requests, asks for missing details, returns a webform when needed, and completes the task after the form is filled.

Collect reimbursement details

Receive reimbursement requests and ask follow-up questions for missing fields.

Return structured webforms

Use A2A webform replies when the client needs to complete missing information.

Example conversation

Input: "I need to submit a travel expense." Output: the agent asks for date, amount, and receipt details, then returns a webform if information is missing.

Technical

Framework

Google ADK

Language

Python

Spec version

1.0-alpha

Interaction

Text, Forms/Structured Data

Supported input

TextJSON

Supported output

TextJSON

Requirements

API keys

Google AI

Infra

Python 3.11+

Estimated run cost

LLM cost only; local sample runtime otherwise.

External services

None

How to install

Clone or access the repository at https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/adk_expense_reimbursement.

Checkout the branch or tag `main`.

Prepare the required runtime: Python 3.11+.

Provision the required API keys: Google AI.

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

Create a `.env` with `GEMINI_API_KEY`, run `uv run .`, then connect with the sample A2A client.

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.