The Ultimate Guide to n8n for PMs, with Pawel Huryn
The Growth Podcast
Token Cost Tradeoffs: Workflow vs Agent
Pawel contrasts token/time: workflows used ~5k tokens while agentic runs consumed many more tokens and time.
Pawel Huryn is the guest behind my most popular episode ever (52K+ views).
Today, he’s back to give you a masterclass in one of the most exciting AI tools out there: n8n.
n8n is the most powerful workflow automation tool that combines two things: traditional workflow automation and building AI agents.
And Pawel has been knee-deep in n8n more than almost anyone else in the world.
He’s tried everything. He’s made all the mistakes. He’s learned all the expert workflows and tips and tricks.
In today’s episode, he walks through building real n8n workflows from scratch.
-----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by:
* Amplitude: The market-leader in product analytics
* Vanta: Automate compliance across 35+ frameworks
* Testkube: Leading test orchestration platform
* Kameleoon: AI experimentation platform
* Pendo: The #1 software experience management platform
-----
Key Takeaways
1. N8N combines traditional workflow automation AND AI agent building in one platform - making it more powerful than Zapier or Make for complex automation needs.
2. Real use cases span from simple business workflows to chatbots, automatic competitor monitoring, multi-agent research systems, and inbox workers that take actions based on emails. Sky is the limit.
3. Pavel's competitor monitoring workflow costs $1-2/week using the FREE version of N8N. Just needs Perplexity API ($1-2 for hundreds of calls) and OpenAI credits. Enterprise tools charge $500+/month.
4. Pin your data during development. N8N caches API responses so you don't burn credits while testing workflows. Click the pin icon and N8N uses cached data instead of making new API calls.
5. N8N automatically loops through items - no need to write for-loops or while-loops. When you connect a node with 6 items, N8N repeats the action 6 times automatically.
6. Compress context before sending to LLMs. Pavel cuts 70% of tokens by extracting only summary content and citation URLs from Perplexity results, ignoring irrelevant snippets and metadata.
7. Use ChatGPT to write N8N code snippets. Pavel never writes code blocks himself - just takes a screenshot of the data and asks GPT "how do I compress this information?"
8. Traditional workflows are more efficient (saves tokens, very reliable) for predictable tasks. AI agents are more flexible but use more tokens and can make mistakes. Use workflows when you know the steps.
9. Set GPT reasoning effort to "low" for simple tasks. When you just need formatting or summarization (not complex thinking), low reasoning effort saves tokens significantly.
10. Best practices: Set dedicated error probes to catch errors before they break workflows. Use max iterations to prevent infinite loops. Set retry on fail to 3x attempts. Pin data during development.
-----
Where to Find Pawel
* YouTube
-----
Related Content
Newsletters:
* Ultimate Guide to AI Prototyping Tools
* AI Agents: The Ultimate Guide for PMs
Podcasts:
* AI Agents Demo, with CEO of Relay.app
* How to Build AI Agents (and Get Paid $750K+)
* 5 AI Agents Every PM Should Build, with CEO of Lindy
If you want access to a n8n competitor for free, get Aakash’s bundle and access to Relay.app.
-----
If you want to advertise, email productgrowthppp at gmail.
The AI-powered Podcast Player
