Skip to main content

Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval

Workflow preview

Workflow preview
100%
Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval preview
Open on n8n.io

1. Workflow Overview

How It Works This workflow automates enterprise resource planning (ERP) operations across Engineering, Finance, HR, and Admin departments for operations managers, ERP administrators, and business p...

Best for

  • Engineering automation workflows
  • AI Chatbot automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.webhook, @n8n/n8n-nodes-langchain.agent, n8n-nodes-base.switch, n8n-nodes-base.merge, n8n-nodes-base.if, n8n-nodes-base.gmail, n8n-nodes-base.slack, n8n-nodes-base.scheduletrigger

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Cheng Siong Chin.

Original n8n.io source

1.1 Workflow description

Title
Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval
Workflow name
Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval

How It Works

This workflow automates enterprise resource planning (ERP) operations across Engineering, Finance, HR, and Admin departments for operations managers, ERP administrators, and business process owners who need intelligent task routing with human oversight. It solves the problem of siloed departmental workflows by centralising all inbound requests through a single Orchestrator Agent that routes tasks to the correct specialist AI agent. Each department agent, namely: Engineering, Finance, HR, and Admin operates with its own LLM model, memory, ERP tool, calculator, and output parser. The Orchestrator routes by department, agents process and return results, which are then combined and evaluated for human approval. Tasks requiring sign-off trigger an approval email; others post directly to Slack. A separate scheduled pipeline runs daily, fetching pending tasks, aggregating them, generating a Daily Report via a Reporting Agent, and emailing it via Gmail.

Setup Steps

  1. Add OpenAI credentials to all agent model nodes (Orchestrator, Engineering, Finance, HR).
  2. Configure ERP tool credentials for each department's ERP node.
  3. Set Slack credentials and target channel in the Notify Team on Slack node.
  4. Add Gmail credentials to Send Approval Email and Email Daily Report nodes.
  5. Connect memory backends (e.g., Redis or n8n memory) to all agent memory nodes.
  6. Set the Schedule trigger interval for daily operations (e.g., 08:00 daily).
  7. Configure the webhook URL for Webhook – External Systems trigger.

Prerequisites

  • OpenAI API key (GPT-4 or GPT-4o)
  • ERP system with API access (per department)
  • Slack workspace with bot token
  • Gmail account with OAuth2 credentials
  • Memory backend (Redis or n8n built-in)

Use Cases

  • Automated engineering change request routing and approval
  • Finance budget approval with human sign-off gate
  • HR onboarding task orchestration across systems
  • Daily ERP operations summary for management review

Customization

  • Add more department agents (e.g., Legal, Procurement) by extending the router
  • Replace Gmail with Outlook or SendGrid for email delivery
  • Swap Slack for Teams or Discord notifications
  • Adjust approval conditions to match your governance thresholds

Benefits

  • Single orchestrator eliminates cross-department routing delays
  • Human approval gate ensures compliance for sensitive ERP actions
  • Daily automated reporting reduces manual ops overhead
  • Modular agent design allows per-department tool customisation

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 - Webhook - External Systems

Type / Role
n8n-nodes-base.webhook - webhook
Config choices
Version 2.1

Block 2 - Orchestrator Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 3 - Route by Department

Type / Role
n8n-nodes-base.switch - switch
Config choices
Version 3.4

Block 4 - Engineering Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 5 - Combine Agent Results

Type / Role
n8n-nodes-base.merge - merge
Config choices
Version 3.2

Block 6 - Finance Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 7 - HR Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 8 - Admin Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 9 - Requires Human Approval?

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

Block 10 - Send Approval Email

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

Block 11 - Notify Team on Slack

Type / Role
n8n-nodes-base.slack - slack
Config choices
Version 2.4

Block 12 - Schedule - Daily Operations

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

Block 13 - Fetch Pending Tasks

Type / Role
n8n-nodes-base.dataTable - dataTable
Config choices
Version 1.1

Block 14 - Aggregate Tasks

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

Block 15 - Generate Daily Report

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 16 - Email Daily Report

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

Block 17 - Orchestrator Model

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

Block 18 - Orchestrator Memory

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

Block 19 - Orchestrator ERP Tool

Type / Role
n8n-nodes-base.httpRequestTool - httpRequestTool
Config choices
Version 4.4

Block 20 - Orchestrator Calculator

Type / Role
@n8n/n8n-nodes-langchain.toolCalculator - toolCalculator
Config choices
Version 1

Block 21 - Orchestrator Parser

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

Block 22 - Engineering Model

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

Block 23 - Engineering Memory

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

Block 24 - Engineering ERP Tool

Type / Role
n8n-nodes-base.httpRequestTool - httpRequestTool
Config choices
Version 4.4

Showing the first 24 of 52 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval
Complexity advanced
Nodes 52
Categories Engineering, AI Chatbot
Author Cheng Siong Chin
Published 09 May 2026

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/15573/15573.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 Route ERP tasks across departments with GPT-4, Slack, Gmail and human approval do?

How It Works This workflow automates enterprise resource planning (ERP) operations across Engineering, Finance, HR, and Admin departments for operations managers, ERP administrators, and business p...

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 Engineering, AI Chatbot use case.