The automation monitors a folder for new bank statement files, checks each transaction against tenant records, and writes action items to an Excel report. It helps property and finance teams find missing or incorrect rent payments fast.

Here is how it works. A local file trigger watches for CSV files and loads the new file. The data is parsed into rows, then an AI agent powered by OpenAI reviews the payments. The agent can call tools that read tenant and property details from the Excel workbook, so it can consider rent amounts, due dates, and notes. A structured parser enforces clean fields like tenant id, action required, and date. The list of actions is split into single items, and a code step appends them to the alerts sheet in the same workbook.

Set this up on a self hosted n8n with access to the local drive. Point the trigger to your bank statement folder, set the spreadsheet path, and add your OpenAI API key. Many teams see monthly reconciliation drop from hours to minutes with fewer missed issues. It fits small property portfolios, accounting teams, and landlords who manage many tenants.

• Folder watcher for new CSV bank statements so files are processed as soon as they arrive.
• CSV parsing to turn statements into structured rows ready for review.
• AI agent with OpenAI to compare payments against rent rules and tenant notes.
• Custom tools read tenant and property data from the Excel workbook.
• Structured output parser enforces a clean schema for alerts and actions.
• List splitter turns the alert list into single items for easy handling.
• Code step appends each action to the alerts sheet in the same workbook.
• Central variable stores the workbook path for simple configuration.

• Reduce monthly reconciliation from 4 hours to 20 minutes
• Cut manual copy and paste errors by up to 70 percent
• Keep sensitive data on local files for stronger privacy
• Handle dozens of tenants without extra admin work
• Connect bank CSV and Excel records into one clean report
• Auto detect new statements and process them with no clicks

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with OpenAI. See the Tools Required section above for links to create accounts with these services.
3. Use a self hosted n8n instance with a mounted folder so the workflow can access local files. Map your host folder into the n8n container and note the internal path.
4. Open the Watch For Bank Statements node and set the folder path to the mounted directory that will receive CSV bank statements. Keep the event on add and filter to CSV files.
5. Open the Set Variables node and update spreadsheet_location to the full path of your workbook. Make sure the workbook exists and contains sheets named tenants, properties, and alerts.
6. Create the OpenAI credential: In n8n go to Credentials > New > OpenAI. Generate an API key in your OpenAI account on the API keys page, paste it into n8n, and save. Name the credential clearly such as OpenAI Prod.
7. Open the OpenAI Chat Model node and choose your OpenAI credential from the dropdown. Pick the model you want to use.
8. Open the Reconcile Rental Payments agent node and confirm it uses the OpenAI Chat Model, the Structured Output Parser, and the two tool nodes for tenant and property lookup.
9. Check the Structured Output Parser schema matches the fields needed by later steps, including tenant_id, action_required, and date.
10. Verify the Alert Actions To List node splits the field named output. If your agent returns a different field name, update this setting.
11. Place a sample CSV bank statement in the watched folder. Run the workflow once to test. Open the alerts sheet in your workbook and confirm new rows were added.
12. Troubleshoot if needed: if files are not detected, check folder permissions and the container mount path. If rows do not write, back up your workbook and review the Code node logs.