HumationHuman + Automation
Back to Catalog

🎓 Learn evaluate tool. Tutorial for beginners with Gemini and Google Sheets

DavideDavide
527 views
2/3/2026
Meeting ManagementAutomationZoomGoogle CalendarScheduling
Official Page

This workflow is a beginner-friendly tutorial demonstrating how to use the Evaluation tool to automatically score the AI’s output against a known correct answer (“ground truth”) stored in a Google Sheet.

Advantages

  • ✅ Beginner-friendly – Provides a simple and clear structure to understand AI evaluation.
  • ✅ Flexible input sources – Works with both Google Sheets datasets and manual test entries.
  • ✅ Integrated with Google Gemini – Leverages a powerful AI model for text-based tasks.
  • ✅ Tool usage – Demonstrates how an AI agent can call external tools (e.g., calculator) for accurate answers.
  • ✅ Automated evaluation – Outputs are automatically compared against ground truth data for factual correctness.
  • ✅ Scalable testing – Can handle multiple dataset rows, making it useful for structured AI model evaluation.
  • ✅ Result tracking – Saves both answers and correctness scores back to Google Sheets for easy monitoring.

How it Works

The workflow operates in two distinct modes, determined by the trigger:

  1. Manual Test Mode: Triggered by "When clicking 'Execute workflow'". It sends a fixed question ("How much is 8 * 3?") to the AI agent and returns the answer to the user. This mode is for quick, ad-hoc testing.
  2. Evaluation Mode: Triggered by "When fetching a dataset row". This mode reads rows of data from a linked Google Sheet. Each row contains an input (a question) and an expected_output (the correct answer). It processes each row as follows:
    • The input question is sent to the AI Agent node.
    • The AI Agent, powered by a Google Gemini model and equipped with a Calculator tool, processes the question and generates an answer (output).
    • The workflow then checks if it's in evaluation mode.
    • Instead of just returning the answer, it passes the AI's actual_output and the sheet's expected_output to another Evaluation node.
    • This node uses a second Google Gemini model as a "judge" to evaluate the factual correctness of the AI's answer compared to the expected one, generating a Correctness score on a scale from 1 to 5.
    • Finally, both the AI's actual_output and the automated correctness score are written back to a new column in the same row of the Google Sheet.

Set up Steps

To use this workflow, you need to complete the following setup steps:

  1. Credentials Configuration:

    • Set up the Google Sheets OAuth2 API credentials (named "Google Sheets account"). This allows n8n to read from and write to your Google Sheet.
    • Set up the Google Gemini (PaLM) API credentials (named "Google Gemini(PaLM) (Eure)"). This provides the AI language model capabilities for both the agent and the evaluator.

  2. Prepare Your Google Sheet:

    • The workflow is pre-configured to use a specific Google Sheet. You must clone the provided template sheet (the URL is in the Sticky Note) to your own Google Drive.
    • In your cloned sheet, ensure you have at least two columns: one for the input/question (e.g., input) and one for the expected correct answer (e.g., expected_output). You may need to update the node parameters that reference $json.input and $json.expected_output to match your column names exactly.

  3. Update Document IDs:

    • After cloning the sheet, get its new Document ID from its URL and update the documentId field in all three Evaluation nodes ("When fetching a dataset row", "Set output Evaluation", and "Set correctness") to point to your new sheet instead of the original template.

  4. Activate the Workflow:

    • Once the credentials and sheet are configured, toggle the workflow to Active. You can then trigger a manual test run or set the "When fetching a dataset row" node to poll your sheet automatically to evaluate all rows.

Need help customizing?

Contact me for consulting and support or add me on Linkedin.

Learn to Evaluate Tools with Gemini and Google Sheets

This n8n workflow demonstrates how to set up an evaluation pipeline for AI agents, specifically focusing on a Gemini-powered agent that can use a Calculator tool. It's designed to help beginners understand how to test and measure the performance of AI tools within n8n.

What it does

This workflow provides a foundational structure for evaluating an AI agent's ability to use a tool. While the specific evaluation logic and dataset are not fully defined in this base template, it sets up the necessary components:

  1. Triggers Evaluation: The workflow is initiated by an "Evaluation Trigger" node, which is typically used to fetch rows from a dataset (e.g., a Google Sheet) containing test cases.
  2. Prepares Input (Optional): An "Edit Fields (Set)" node is included to potentially transform or prepare the input data from the dataset before it's fed to the AI agent.
  3. Executes AI Agent: An "AI Agent" node (powered by LangChain) takes the prepared input.
  4. Utilizes Google Gemini: The AI Agent is configured to use the "Google Gemini Chat Model" as its underlying language model.
  5. Leverages Calculator Tool: The AI Agent is also equipped with a "Calculator" tool, allowing it to perform mathematical operations when needed.
  6. Performs Evaluation: An "Evaluation" node is included to compare the AI agent's output against expected results from the dataset, calculate metrics, and record the evaluation outcome.
  7. No Operation: A "No Operation" node is present, likely as a placeholder or for debugging purposes, indicating a point where no action is taken.

Prerequisites/Requirements

  • n8n Instance: A running n8n instance.
  • Google Gemini API Key: Access to the Google Gemini API and a corresponding API key configured as an n8n credential.
  • Google Sheets (Implicit): While not explicitly connected in this barebones JSON, the "Evaluation Trigger" strongly implies the use of a Google Sheet or similar data source for evaluation datasets. You would need a Google Sheet with test cases (prompts, expected answers, etc.).
  • LangChain Integration: The n8n LangChain nodes (@n8n/n8n-nodes-langchain) must be installed and available in your n8n instance.

Setup/Usage

  1. Import the workflow: Import the provided JSON into your n8n instance.
  2. Configure Google Gemini Credentials:
    • Find the "Google Gemini Chat Model" node.
    • Configure your Google Gemini API key as a credential within n8n and select it in the node's settings.
  3. Prepare Evaluation Dataset:
    • Create a Google Sheet (or similar) with your evaluation data. This sheet should contain columns for prompts, expected answers, and any other relevant information for testing your AI agent.
  4. Configure Evaluation Trigger:
    • Edit the "Evaluation Trigger" node to connect to your prepared dataset (e.g., a Google Sheet node, if you're using one to fetch rows).
    • Ensure it fetches the necessary input for your AI agent and the expected output for evaluation.
  5. Refine "Edit Fields (Set)" (Optional):
    • If your input data needs transformation, configure the "Edit Fields (Set)" node to structure the data correctly for the "AI Agent" node.
  6. Configure "AI Agent":
    • Review the "AI Agent" node settings. Ensure the "Google Gemini Chat Model" and "Calculator" tools are correctly selected and configured.
  7. Implement Evaluation Logic:
    • The "Evaluation" node is where you define how the AI agent's output will be compared against the expected results from your dataset. You'll typically use expressions to access the agent's output and the expected values, then define metrics (e.g., accuracy, correctness) to be calculated.
  8. Execute the workflow: Once configured, you can execute the workflow. The "Evaluation Trigger" will iterate through your dataset, running the AI agent for each row and recording the evaluation results.

Related Templates

Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets

This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.

Ranjan DailataBy Ranjan Dailata
161

Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax

Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions

Daniel NkenchoBy Daniel Nkencho
601

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

Le NguyenBy Le Nguyen
942