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

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 expectedoutput (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 actualoutput and the sheet's expectedoutput 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 actualoutput and the automated correctness score are written back to a new column in the same row of the Google Sheet.

---