Benchmark content safety guardrails with automated test suite & reports
Ready for 3.0Ready 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 13 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model, Guardrails and Gmail.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Test Data (code) (Code): runs custom JavaScript code
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Calculate Metrics (Code): runs custom JavaScript code
- Preserve Original Data (Code): runs custom JavaScript code
- Format Report (Code): runs custom JavaScript code
- Check Guardrails (Guardrails): uses Guardrails, with model: OpenAI Chat Model
- Markdown: converts between Markdown and HTML
- Format Pass Result (Code): runs custom JavaScript code
- Format Fail Result (Code): runs custom JavaScript code
- Send a message (Gmail): uses Gmail
…plus 1 more step. See the full node list below.
Services it uses
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.
Nodes used (8)
- Manual Trigger
n8n-nodes-base.manualTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Guardrails
@n8n/n8n-nodes-langchain.guardrails - Code
n8n-nodes-base.code - Merge
n8n-nodes-base.merge - Gmail
n8n-nodes-base.gmail - Markdown
n8n-nodes-base.markdown
From the author
🛡️ Evaluate Guardrails Node Accuracy with Automated Test Suite This workflow benchmarks the n8n Guardrails node across multiple safety categories -including PII, NSFW, jailbreak attempts, secret keys, and unsafe URLs. It runs 36 structured test cases,…