Skip to main content

Review and approve employee expenses with forms, OpenAI and Google Workspace

Workflow preview

Workflow preview
100%
Review and approve employee expenses with forms, OpenAI and Google Workspace preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

How it works This workflow automates employee expense reimbursements from submission to final resolution. Expenses are captured via a form, reviewed by an AI agent for justification, and routed to ...

Best for

  • Document Extraction automation workflows
  • AI Summarization automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.formtrigger, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenai, n8n-nodes-base.if, n8n-nodes-base.googlesheets, @n8n/n8n-nodes-langchain.outputparserstructured, n8n-nodes-base.gmail, n8n-nodes-base.googlecalendartool

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Avkash Kakdiya.

Original n8n.io source

1.1 Workflow description

Title
Review and approve employee expenses with forms, OpenAI and Google Workspace
Workflow name
Review and approve employee expenses with forms, OpenAI and Google Workspace

How it works

This workflow automates employee expense reimbursements from submission to final resolution. Expenses are captured via a form, reviewed by an AI agent for justification, and routed to managers for approval or clarification. Approved expenses notify employees instantly, while rejected or unclear cases automatically schedule a follow-up discussion. All actions are logged to keep finance records clean and auditable.

Step-by-step

  • Step 1: Capture, summarize, and request approval

    • On Expense Form Submission – Captures structured expense details submitted by employees.
    • Append row in sheet – Stores each expense entry in Google Sheets for tracking.
    • AI Agent – Reviews the expense description and validates whether the full amount is justified.
      • OpenAI Chat Model – Powers the AI reasoning used to analyze the expense.
      • Output Parser – Converts the AI response into a structured decision format.
    • If – Routes the flow based on whether the expense is appropriate or not.
  • Step 2: Manager reviews and responds

    • Send Email to Manager for Approval – Sends an approval email when the expense is justified.
    • Send Email to Manager for Approval1 – Sends a clarification-required email when justification is unclear.
    • If1 – Checks the manager’s approve or reject response from the email.
  • Step 3: Notify employee or schedule discussion

    • Send a message – Notifies the employee when the expense is approved.
    • Booking Agent – Automatically finds the next available business-day time slot if the expense is rejected.
      • OpenAI – Interprets availability rules and slot selection logic.
      • Get Events – Fetches existing calendar events for the selected day.
      • Check Availability – Identifies free time slots within working hours.
      • Output Parser1 – Structures the selected meeting time.
    • Send a message2 – Emails the employee with discussion details when clarification is required.

Why use this?

  • Enforce consistent expense validation before manager review.
  • Reduce manual back-and-forth between employees, managers, and finance.
  • Keep a centralized, auditable record of all expense submissions.
  • Speed up reimbursements with automated approvals and notifications.
  • Handle rejected expenses professionally with automatic discussion scheduling.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - On Expense Form Submission

Type / Role
n8n-nodes-base.formTrigger - formTrigger
Config choices
Version 2.3

Block 2 - AI Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3

Block 3 - OpenAI Chat Model

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.3

Block 4 - If

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.3

Block 5 - Append row in sheet

Type / Role
n8n-nodes-base.googleSheets - googleSheets
Config choices
Version 4.7

Block 6 - Output Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 7 - Send Email to Manager for Approval

Type / Role
n8n-nodes-base.gmail - gmail
Config choices
Version 2.2

Block 8 - Send Email to Manager for Approval1

Type / Role
n8n-nodes-base.gmail - gmail
Config choices
Version 2.2

Block 9 - If1

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.3

Block 10 - Send a message

Type / Role
n8n-nodes-base.gmail - gmail
Config choices
Version 2.2

Block 11 - Check Availability

Type / Role
n8n-nodes-base.googleCalendarTool - googleCalendarTool
Config choices
Version 1.3

Block 12 - Get Events

Type / Role
n8n-nodes-base.googleCalendarTool - googleCalendarTool
Config choices
Version 1.3

Block 13 - OpenAI

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 14 - Booking Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2.2

Block 15 - Output Parser1

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 16 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 17 - Sticky Note1

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 18 - Sticky Note2

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 19 - Send a message2

Type / Role
n8n-nodes-base.gmail - gmail
Config choices
Version 2.2

Block 20 - Sticky Note7

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

3. Summary Table

Workflow Review and approve employee expenses with forms, OpenAI and Google Workspace
Complexity advanced
Nodes 20
Categories Document Extraction, AI Summarization
Author Avkash Kakdiya
Published 29 Dec 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/12256/12256.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Review and approve employee expenses with forms, OpenAI and Google Workspace do?

How it works This workflow automates employee expense reimbursements from submission to final resolution. Expenses are captured via a form, reviewed by an AI agent for justification, and routed to ...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Document Extraction, AI Summarization use case.