🔧 Reconcile and diagnose discrepancies between two CSV exports with Gemini
⚡ 33 views · 🔧 Miscellaneous
Description
Quick Overview
This workflow collects two CSV exports via an n8n form, reconciles them by a user-specified key and amount column, and uses Google Gemini to diagnose likely systemic causes of any drift, returning either a “balances” confirmation or a downloadable Excel reconciliation workbook.
How it works
- Receives an n8n form submission where the user describes the reconciliation, specifies the linking and amount columns, and uploads two CSV files.
- Extracts both CSV files into structured rows and compares the datasets by the chosen key column to identify matches, mismatches, and missing records.
- Groups results into four buckets (agrees, values disagree, only in the source of truth, only in your records) and calculates counts, totals, and the net gap.
- Sends the reconciliation summary and representative examples to Google Gemini and parses the response into a structured diagnosis with likely causes, checks, and materiality.
- If everything balances, returns a completion page confirming there are no differences.
- If differences exist, builds an Excel workbook that starts with the diagnosis and then lists every differing row by bucket, and returns it as a download from the form.
Setup
- Add a Google Gemini (PaLM) API credential for the language model used to generate the drift diagnosis.
- Open the form trigger and copy the production form URL if you want to share it with teammates.
- Export both systems as CSV files with a header row, and ensure both contain the linking column and the amount column you enter in the form.
🔗 Nodes Used
Basic LLM Chain, Structured Output Parser, n8n Form Trigger, Convert to File, Extract from File, Google Gemini Chat Model
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File