Benchmark content safety guardrails with automated test suite & reports

🛡️ 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, classifies each as PASS or VIOLATION, calculates accuracy metrics, and emails a detailed HTML report. 🔄 How it works The workflow loops through 36 predefined test prompts. Each prompt is checked by the Guardrails node for violations. Results are recorded as PASS or VIOLATION. The system calculates metrics (accuracy, precision, recall, F1). A formatted Markdown → HTML report is generated and sent via Gmail. ⚙️ Set up steps Add your OpenAI and

Help me set up the n8n workflow "Benchmark content safety guardrails with automated test suite & reports" (https://n8n.io/workflows/10729). It uses: Gmail, Code, OpenAI Chat Model, Guardrails. Import the template JSON into my n8n instance, list every credential I need to create, and walk me through testing it.