Making LLMs reliable: How to test your LLM blocks in n8n

Hosted by Amir Feizpour and Lena Shakurova

Fri, Jul 18, 2025

4:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Build Multi-Agent Applications - A Bootcamp - LangGraph, Cursor, n8n
Amir Feizpour, PhD
View syllabus

What you'll learn

A simple way to create test sets for your LLM blocks in n8n

How to build a testing workflow inside n8n

Refining prompts in n8n to get repeatable results

Why this topic matters

Building n8n automations with LLM blocks is quite popular, yet a lot of people struggle with getting those blocks to behave consistently. LLMs are non-deterministic, which means your automation might work today and fail tomorrow. I will show you how to set up prompt testing inside n8n so your outputs stay repeatable, your automations don’t flake out, and you can trust what you’ve built.

You'll learn from

Amir Feizpour

Founder @ Aggregate Intellect

Amir Feizpour is the founder, CEO, and Chief Scientist at Aggregate Intellect building a generative business brain for service and science based companies. Amir has built and grown a global community of 5000+ AI practitioners and researchers gathered around topics in AI research, engineering, product development, and responsibility. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir also serves the AI ecosystem as an advisor at MaRS Discovery District, works with several startups as fractional chief AI officer, and engages with a wide range of community audiences (business executives to hands-on developers) through training and educational programs. Amir leads Aggregate Intellect’s R&D via several academic collaborations.

Lena Shakurova

Founder @ ParsLabs

Lena Shakurova is the founder & CEO at ParsLabs, Conversational AI agency and Chatbotly, a no-code platform for building AI assistants trained on custom data. Since 2018+, her agency helped 100+ companies with their AI projects, from strategy to production. Prior to this, Lena worked as an NLP Research Engineer and Full-Stack Developer. Lena focuses on ethical, user-first AI, leveraging her expertise in Linguistics & AI to create responsible AI solutions that drive business results. She shares insights on AI innovation and human-centered design through her blog, LinkedIn and YouTube channel.

Learn directly from Amir Feizpour and Lena Shakurova

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.