Templates / Evaluate AI workflows using Google Sheets, Gemini, Claude, GPT, and Perplexity

Evaluate AI workflows using Google Sheets, Gemini, Claude, GPT, and Perplexity

Ready for 3.0

by Ryan Nolan ✓ · 2,043 views · created 2026-01-11 · Engineering, AI Summarization

Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 49 nodes and runs on Evaluation events (plus 7 other triggers). Along the way it connects Evaluation, Google Gemini Chat Model, Anthropic Chat Model and Perplexity and 2 more.

How it runs

Trigger: On Evaluation events (plus 7 other triggers).

  1. Information Extractor: extracts structured fields from text with AI, with model: Google Gemini Chat Model
  2. Extract from File: extracts data from a file
  3. World Series Searcher (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
  4. World Series Searcher (AI Agent): runs an AI agent, with model: Anthropic Chat Model; 1 tool (Perplexity Tool)
  5. US Postal Formatter (AI Agent): runs an AI agent, with model: Anthropic Chat Model
  6. Product Description Rewriter (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
  7. Article Reviewer (Summarization Chain): summarizes text with AI, with model: Google Gemini Chat Model
  8. Evaluation: check if evaluating
  9. Evaluation: check if evaluating
  10. Evaluation: check if evaluating

…plus 22 more steps. See the full node list below.

Services it uses

EvaluationGoogle Gemini Chat ModelAnthropic Chat ModelPerplexityOpenAI Chat ModelGmail

Before you upgrade to n8n 3.0

Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.

  • Still check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll) (Gmail Trigger).

Nodes used (13)

From the author

This template and YouTube video goes over 5 different implementations of evaluations within n8n. - Categorization - Correctness - Tools used - String similarity - Helpfulness You’ll learn when to use each type, how to set up test datasets in Google Sheets or…

Excerpt from Ryan Nolan's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.