Skip to content
Aakash GuptaAakash Gupta

Master 80% of n8n in 59 mins

Pawel Huryn has built more N8N workflows than almost anyone. He walks through building real workflows from scratch - from competitor monitoring to AI agents. Here's everything you need to master the most powerful workflow automation tool. Summary: https://www.news.aakashg.com/p/pawel-huryn-podcast Transcript: https://www.aakashg.com/mastering-n8n-how-to-build-powerful-ai-workflow-automations/ ---- Timestamps 0:00 - Intro 1:55 - Why n8n Matters 3:14 - Building Competitor Monitoring Workflow 8:44 - Cost & Free Version Benefits 12:09 - Ads 13:53 - Workflow Automation Deep Dive 19:57 - Traditional Workflow vs AI Agent 23:13 - Building an AI Agent 31:50 - Ads 34:11 - Agent Workflow Results 40:36 - n8n Best Practices 45:35 - Multi-Agent Research System 49:04 - PM Use Cases & Automation 51:12 - Free Version Hacks 57:57 - Outro ---- 🏆 Thanks to our sponsors: 1. Amplitude: The market-leader in product analytics - https://amplitude.com/session-replay?utm_campaign=session-replay-launch-2025&utm_source=linkedin&utm_medium=organic-social&utm_content=productgrowthpodcast 2. Vanta: Automate compliance across 35+ frameworks - http://vanta.com/aakash 3. Testkube: Leading test orchestration platform - http://testkube.io/ 4. Kameleoon: AI experimentation platform - http://www.kameleoon.com/ 5. Pendo: the #1 Software Experience Management Platform - http://www.pendo.com/aakash ---- 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. Pawel'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 Pavel Huryn: LinkedIn: https://www.linkedin.com/in/pavelhuryn/ X: https://twitter.com/pavolhuryn Company: https://www.n8n.io 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com #n8n #ProductManagement --- About Product Growth: The world's largest podcast focused solely on product + growth, with over 187K listeners. Hosted by Aakash Gupta, who spent 16 years in PM, rising to VP of product, this 2x/week show covers product and growth topics in depth. Subscribe and turn on notifications to get more videos like this.

Pawel HurynguestAakash Guptahost
Jan 5, 202658mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Master n8n fast: build workflows, agents, and cost-conscious automation

  1. The episode builds a competitor-monitoring automation end-to-end, starting with a traditional n8n workflow that pulls competitors from Google Sheets, queries Perplexity, formats via OpenAI, converts Markdown to HTML, and emails a report via Gmail.
  2. Pawel contrasts “workflow + LLM step” versus “agentic workflows” versus “true agents,” showing that more autonomy can improve output quality but dramatically increases token usage, cost, and hallucination risk.
  3. The tutorial emphasizes context engineering tactics—pinning node outputs during development, compressing noisy tool responses, aggregating items, and converting structured objects to JSON strings for LLM prompts.
  4. Operational best practices include error workflows, increasing agent max-iterations, enabling retry-on-fail for flaky tool calls, and improving tool descriptions so agents use tools correctly (including parallelization where possible).
  5. The conversation closes with advanced patterns (multi-agent research orchestrators) and pragmatic “free version” workarounds like self-hosting for retention/execution limits and using data tables plus automated workflow exports for globals and version history.

IDEAS WORTH REMEMBERING

5 ideas

Start deterministic when you can; use agents only for genuinely variable work.

Pawel argues the most reliable, cheapest production systems are explicit workflows with LLMs doing bounded tasks, while agents are best reserved for open-ended cognitive work where you can’t pre-map every path.

Agent autonomy can multiply token spend without obvious time savings.

In the demo, the agentic workflow jumps to ~12k tokens and ~1.5 minutes, while the “true agent” reaches ~90k tokens with similar runtime—showing cost scales faster than latency improvements.

Pin node outputs while building to avoid re-calling paid APIs.

Pinning Google Sheets/Perplexity outputs lets you iterate on downstream formatting and email steps without repeatedly paying for searches or re-fetching data.

Compress tool outputs before sending them to an LLM.

Perplexity returns lots of metadata (snippets, titles, etc.); selecting only “content” plus citations reduces tokens, cost, and the chance the model latches onto irrelevant context.

Use aggregation to turn many items into one promptable payload.

n8n auto-iterates over collections, but summarization/reporting often needs a single consolidated input; the aggregate step creates one field from multiple competitor results.

WORDS WORTH SAVING

5 quotes

In my opinion, n8n is the most powerful workflow automation tool.

— Pawel Huryn

Everything that can be automated can be designed and mapped in n8n.

— Pawel Huryn

This would be compressing the context, which means that we select only information that matter and we ignore everything else.

— Pawel Huryn

This was a standard workflow… This one is more agentic, although the agency is pretty limited here.

— Pawel Huryn

In this one here it was 90,000 tokens.

— Pawel Huryn

Competitor monitoring workflow (Sheets → Perplexity → OpenAI → Gmail)Pinning data to speed development and reduce API spendContext compression and token-cost optimizationAggregation and JSON-to-string prompt plumbingWorkflow vs agentic workflow vs true agent tradeoffsAgent settings: max iterations, retries, tool descriptionsFree-plan hacks: self-hosting, data tables, workflow backups/versioning

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome