# AI-powered fuzzy matching, and assigns confidence scores.: n8n workflow > Started by another system calling it, and works across Google Sheets and Slack. It hands the judgement calls to OpenAI. Source: https://millionrounds.com/workflow/ai-powered-fuzzy-matching-and-assigns-confidence-scores (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) · [Chat assistants](https://millionrounds.com/workflows?category=Chat+assistants#library) # AI-powered fuzzy matching, and assigns confidence scores. Started by another system calling it, and works across Google Sheets and Slack. It hands the judgement calls to OpenAI. 24 steps, 3 branches: large, and worth reading before you trust it with anything live. Large Calls a model: OpenAI [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-fuzzy-matching-and-assigns-confidence-scores) **24 steps** Large: read it before trusting it with anything live **3** Branches: places the flow splits **0** Loops or waits **2** Services it connects to ## The flow Starts it 1 Model 3 Logic 17 Service 3 The steps in the order they run, from what starts it. - 1 **Webhook - Receive Financial Data** Webhook *Starts it* - 2 **OpenAI Chat Model** Lm Chat Open Ai *Model* - 3 **Structured Output Parser** Output Parser Structured *Model* - 4 **Workflow Configuration** Set *Logic* - 5 **AI Fuzzy Matching Agent** Agent *Model* - 6 **Check Data Source Type** If *Logic* - 7 **Merge Matched Results** Merge *Logic* - 8 **Normalize Bank Statement Schema** Set *Logic* - 9 **Normalize Invoice Schema** Set *Logic* - 10 **Normalize ERP Schema** Set *Logic* - 11 **Extract CSV Data** Extract From File *Service* - 12 **Calculate Confidence Scores** Code *Logic* - 13 **Merge All Normalized Data** Merge *Logic* - 14 **Merge All Normalized Data1** Merge *Logic* - 15 **Normalize CSV Schema** Set *Logic* - 16 **Route by Confidence Threshold** If *Logic* - 17 **Merge All Normalized Data2** Merge *Logic* - 18 **Mark as Auto-Reconciled** Set *Logic* - 19 **Flag for Human Review** Set *Logic* - 20 **Deterministic Matching Logic** Code *Logic* - 21 **Merge All Results** Merge *Logic* - 22 **Check Match Quality** If *Logic* - 23 **Log to Reconciliation Report** Google Sheets *Service* - 24 **Notify Finance Team** Slack *Service* ## How it's built - **Starts on:** Another system calling it - **Steps:** 24, with 3 branches - **Size:** Large: read it before trusting it with anything live - **Connects to:** Google Sheets, Slack - **Model:** OpenAI ## Questions What does it need to run? An n8n account, plus your own Google Sheets and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included. What starts it? It starts on another system calling it. Does it use AI? Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n. How long does it take to set up? Take your time. At 24 steps it is large: read it before trusting it with anything live. How do I import it? Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts. **Before you run it** Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 24 steps before you point it at anything that matters. ## Run it in n8n - **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n) - **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-fuzzy-matching-and-assigns-confidence-scores) - **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts. Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind. ## Connects to Each opens the other workflows that use it. [Google Sheets](https://millionrounds.com/workflows?service=Google+Sheets#library)[Slack](https://millionrounds.com/workflows?service=Slack#library) ## Workflows like it Also chat assistants, with the same services where possible, closest in size first. - [**AI-Powered NPM Package Intelligence Agent with OpenAI** 24 steps · calls a model · GitHub, Slack](https://millionrounds.com/workflow/ai-powered-npm-package-intelligence-agent-with-openai) - [**Analyze pharma label change impact with Claude and Slack** 24 steps · calls a model · Email, Slack](https://millionrounds.com/workflow/analyze-pharma-label-change-impact-with-claude-and-slack) - [**Audit and cancel unused SaaS seats with Google Sheets** 24 steps · calls a model · Google Sheets, Slack](https://millionrounds.com/workflow/audit-and-cancel-unused-saas-seats-with-google-sheets) - [**Benchmark employer brand on Glassdoor with Bright Data** 24 steps · calls a model · Slack, n8n data table](https://millionrounds.com/workflow/benchmark-employer-brand-on-glassdoor-with-bright-data) - [**Compare products and generate visual scorecards in Telegram** 24 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/compare-products-and-generate-visual-scorecards-in-telegram) - [**Detect and enforce abuse cases with OpenAI and Slack** 24 steps · calls a model · Email, Slack](https://millionrounds.com/workflow/detect-and-enforce-abuse-cases-with-openai-and-slack)