
Hosted by Dylan Watkins - n8n · EN
Welcome to The n8n Masterclass. I’m Dylan Watkins.
Each week we break down real business wins using n8n and AI automation. You’ll learn what worked, why it worked, and what broke along the way. Founders, automation experts, and AI agencies share how they use n8n to simplify operations, scale delivery, and move faster without adding more people.
The n8n Masterclass is not about tutorials or tech jargon. It focuses on the real business side of automation, the frameworks, decision patterns, and creative problem solving that turn workflows into results.
You’ll leave every episode with one principle, one pattern, and one action you can apply this week to grow your business, reduce manual work, and unlock the potential of automation.
If you’re building a business that runs on smart systems, AI, and no-code tools, this is your playbook for scaling with n8n. Follow The n8n Masterclass and start using automation as your competitive edge.

Milorad, n8n's MCP creator, joins the podcast to show you exactly how to get more out of the n8n instance-level MCP server, walking through three real builds from scratch, live on screen.The episode is structured as a progressive masterclass: Level 1 is a deterministic form submission workflow with a data table and email notification, Level 2 is an AI agent that generates LinkedIn posts and can be triggered straight from your phone, and Level 3 is a multi-agent orchestration system where two models (Claude and GPT) independently review the same content and a third orchestrator merges their findings.Along the way, they dig into the real reasons to pair n8n with an LLM client, including credential management, workflow observability, and the security tradeoffs baked into the MCP design. There's also a practical discussion on why iterating step by step beats trying to one-shot complex automations.The conversation closes with a look at what's coming next, including chaining n8n MCP with third-party MCP servers, and an honest preview of what's still in development.🎙 Chapters:00:00 - What We're Building Today00:20 - Three Levels of MCP Mastery01:00 - Level 1: Building a Workflow via Chat02:19 - Creating Data Tables and Form Triggers08:20 - Adding Email Notifications to the Workflow08:55 - Why Use n8n Alongside Claude16:40 - Level 1 Complete: What You Can Do Now17:26 - Level 2: Building an AI LinkedIn Post Agent22:37 - Triggering Workflows From Your Phone30:00 - Level 2 Wrap-Up and Human-in-the-Loop30:01 - Security, Permissions, and Community Nodes44:33 - Level 3: Multi-Agent Orchestration44:37 - Two Models Reviewing the Same Content42:00 - Building Iteratively vs. One-Shotting44:31 - Level 3 in Action42:01 - Connecting n8n MCP to Other MCP Servers44:36 - Preview Status and What's Coming NextGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

Get the open-source incident response workflow here: https://go.n8n.io/incident-responseAnthropic's Mythos AI just found a 27-year-old security bug in OpenBSD that no human ever caught. Days later the US government pulled both Mythos 5 and the public Fable 5 model, worried that same power could be weaponized into cyberattacks. The threat is no longer theoretical, and if your defense isn't automated too, you're already behind.Dylan sits down with Viraj, a former n8n team member turned forward-deployed engineer, who now helps enterprise companies build AI-powered security systems. They walk through a live demo of an open-source cybersecurity workflow built with n8n and backed by real incident data.The conversation covers how to bring AI into SecOps without letting it run wild, why historical incident data and playbooks matter more than the model you choose, and how Anthropic's Mythos is changing the threat landscape by chaining multiple vulnerabilities in a single attack. They also dig into real-world social engineering scams, phishing tactics, and why good data hygiene is the unsexy foundation that makes any AI system actually work.The bigger takeaway: the models will keep getting smarter, but the companies (and individuals) who win are the ones with clean data, solid playbooks, and a workflow harness that can plug in whatever model comes next. This is a practical blueprint for fighting AI-powered threats with your own AI-powered defense.🎙 Chapters:00:00 - AI Found a 27-Year-Old Bug00:37 - What the Demo Covers02:43 - Test Incidents, Playbooks & Data06:11 - Live Phishing Workflow Demo07:08 - Three Branches of Analysis09:35 - Threat Intelligence Explained12:31 - Mythos and Zero-Day Threats15:20 - Why Data Hygiene Matters16:36 - Workflow Results Walkthrough21:07 - Social Engineering and Scams25:07 - Actionable Remediation Steps30:53 - Data Ingestion for Companies34:50 - Forward-Deployed Engineering38:51 - Local Models and Personal Security40:41 - Where to Find VirajGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

If you want this home security setup, go here: https://go.n8n.io/buddyYou get the free step-by-step guide and Buddy's self-hosted cyber lab.Your home network is being probed right now, and most people have no idea. Buddy, a cybersecurity professional and solutions engineer at n8n, built two automation workflows that change that.In this episode, Buddy walks through how to use n8n to automatically scan incoming Gmail for phishing links using VirusTotal, and how to monitor your firewall for blocked threats, enriching each alert with VirusTotal, URLScan, and MISP in under 10 seconds.These workflows work for homeowners with a smart device setup and for small businesses protecting employee inboxes alike. Buddy covers phishing detection, firewall threat enrichment, lateral movement, ransomware, prompt injection risks, and personal data exposure from breaches like National Public Data.The conversation ends with a practical cybersecurity checklist: password managers, app-based two-factor authentication, social media verification, and keeping software updated. Links to the workflows, the GitHub repo, a setup guide, and a hardware recommendation are all below.🎙 Chapters:00:00 - Intro: What This Episode Covers01:48 - Phishing Email Workflow Demo05:50 - What Is VirusTotal?07:00 - Auto-Tagging Confirmed Phishing in Gmail09:27 - Real-World Phishing Attack Stories14:00 - Lateral Movement and Ransomware Explained16:08 - Firewall Monitoring Workflow and Ubiquiti Setup20:00 - Geo-Blocking and Incoming Connection Threats21:44 - URLScan, MISP, and Threat Enrichment27:53 - Full Workflow Walkthrough: Soup to Nuts37:07 - Dark Web Data Exposure and Identity Theft43:41 - Why Use n8n for Cybersecurity Automation46:23 - AI Agents, Prompt Injection, and Future Threats48:47 - Personal Security Checklist and Best Practices52:11 - Closing Thoughts and Next StepsGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

Most people hear about Claude's Cowork features and wonder how it actually fits into a real automation stack. This episode is the answer: a full walkthrough of connecting Claude Cowork to n8n, building a production-ready email classifier from scratch, and the token-saving tricks that make it all sustainable.Ryan Nolan, who runs a data science YouTube channel and deploys AI automations at his day job, joins the n8n podcast to share his exact playbook for pairing these two tools.The conversation covers setting up the n8n connector in under 60 seconds, calling external APIs through n8n workflows, building an email classifier with human-in-the-loop approval and error handling, and the new Google sign-in flow that eliminates the painful credential setup process. They also dig into why Claude's computer control is too slow for real scraping, and how n8n workflows are a better fit.On the enterprise side, Ryan explains why compliance teams need structured execution logs (not just Cowork skill histories), how to roll out AI automation department by department, and the hackathon where a team with zero n8n experience built a driver's license verification workflow in two days.🎙 Chapters:00:00 - Introduction and episode overview02:23 - Connecting n8n to Claude Cowork04:21 - Calling APIs from Cowork via n8n10:27 - Building an email classifier workflow14:51 - Tips for prompting and iterating13:42 - Compliance and audit logging24:10 - Saving tokens with n8n workflows32:31 - Enterprise security and skills vs workflows36:48 - Reviewing the built workflow39:41 - Quick Google credential setup42:10 - Execution history and debugging44:01 - The hackathon story46:45 - Advice for getting started51:43 - Running with David GogginsGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

🎁 Link to Enterprise Playbook 👉 https://go.n8n.io/n8n-enterprise-playbookMost companies trying to roll out AI get stuck at five or ten workflows. Fullscript, a health tech company with over a thousand employees, built more than 1,500 in under a year (with over a hundred in production) and saved tens of thousands of hours doing it.Sahar Rahmani is the Director of Internal AI at Fullscript. She walks through exactly how they went from engineering-bottlenecked automation requests to company-wide self-service AI adoption using n8n.The conversation covers their hackathon launch strategy, the template library and global credentials trick that removed barriers for non-technical teams, and the highest-value workflows they built across sales, finance, legal, and customer support. If you're looking for a practical enterprise AI automation playbook, this is it.Sahar also shares how they shifted their messaging from "AI first" to "people first, AI powered," and why that cultural reframe was the key to getting real buy-in across every department.🎙 Chapters:00:00 - Intro and Fullscript's AI results02:12 - The state of automation before n8n03:56 - Workshops, templates, and credentials06:33 - Why the templates actually worked09:44 - The company-wide AI hackathon13:31 - Hackathon advice: start small20:05 - Sales lead scoring automation24:37 - ROI: tens of thousands of hours saved27:20 - Finance invoice reconciliation32:48 - The Director of Internal AI role33:48 - Overcoming employee resistance to AI38:00 - Customer support call automation42:22 - Legal contract review with local AI44:56 - Keeping momentum after launch48:42 - Final advice and where to find SaharGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

What if AI could let anyone (not just engineers) build real software? In this impromptu podcast recorded live outside Google Next, Olof Hedin of Lovable sits down with the n8n team to explore how vibe coding is democratizing software creation and reshaping entire industries.Olof shares the origin story of Lovable, from a viral GitHub prototype to one of the fastest-growing companies of all time. The conversation dives into how non-technical users (from nurses at HCA Healthcare to a Brazilian entrepreneur who built a $500K safety app) are building production-ready software with simple prompts. Olof breaks down the n8n and Lovable MCP partnership, the enterprise adoption playbook including customers like NVIDIA with the emerging tech stack of AI agents, workflow automation, and no-code front ends that's threatening legacy software giants like SAP and Salesforce. They also discuss what the future holds for solo founders, the one-person billion-dollar company, and the security risks of giving AI agents too much power.🎙 Chapters:00:00 - Highlights & Teaser00:40 - Live From Google Next02:54 - The Origin Story of Lovable04:17 - Internal Tools & Vibe Coding06:26 - The n8n x Lovable Partnership09:22 - Breaking Down Data Silos14:54 - Nurses Vibe Coding at HCA16:27 - The $500K Safety App From Brazil23:25 - What Makes Lovable Different26:24 - Enterprise Adoption Barriers31:28 - The One-Person Billion-Dollar Company34:54 - Advice for Aspiring Builders40:15 - Hopes, Fears & AI Security42:00 - Closing ThoughtsGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

🔗 n8n Desk (GitHub): https://go.n8n.io/n8ndesk-github🔗 n8n Desk (Website): https://go.n8n.io/n8ndesk-websiteWhat if you could use Claude Code to build n8n workflows and never worry about it running destructive code on your machine?In this episode, Marcel joins the show to demo two things: n8n's brand new official MCP server (currently in beta), which lets AI agents build workflows for the first time, not just run them. And then his own open source project, n8n Desk: a free desktop app that looks and feels like Claude Desktop, but routes all code execution through n8n instead of your local machine.That means encrypted credentials, a full audit trail, support for any AI model (including local ones), and role-based access for enterprise teams.We also get into vibe flowing, context engineering, and why n8n is actually easier to debug than AI-generated code.Timestamps0:00 - Claude Code destructive actions story1:40 - Guest intro & today's topics1:45 - New ways to build n8n workflows4:05 - Connecting n8n MCP to Claude Code5:01 - Old MCP vs. new MCP5:25 - New MCP builds workflows5:33 - Any agent can create workflows6:47 - What is "vibe flowing"?7:41 - Why n8n is easier to debug11:32 - AI fatigue & reclaiming your time11:37 - Setting up the n8n MCP connector12:50 - Building an IT support buddy agent13:22 - Vibe coding vs. context engineering15:14 - Agent creates workflow inside n8n17:31 - Why the first attempt failed17:35 - MCP ships built-in reference skills19:22 - Community MCP & combining skill stores20:43 - Custom skill stores & plugins23:13 - Skills as .md files explained24:21 - Latest & greatest, expect improvements24:29 - Marcel's side project teaser24:42 - The problem with Claude Desktop28:24 - Introducing n8n Desk28:30 - Run any AI model locally30:34 - Cowork tab: local files via n8n37:20 - Chat Hub: talk to n8n agents38:03 - Kelly calendar agent live demo42:20 - Free & open source release planspodscan_22hDOpmUwVdA34BDKTOUH48A6pgDQE93Get 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

Most HR teams are still setting up Slack, email, and Jira accounts by hand every time someone new joins. And when requests come in from three different places at once? Someone has to manually sort through all of it.In this episode, I sit down with Paul Karrmann — an automation consultant based in Germany who built two n8n workflows that fix both of these problems.🔗 Free HR Template: https://go.n8n.io/hr-template🔗 Personio Community Node: https://go.n8n.io/personio-npm──────────────────────────WHAT WE COVERWorkflow #1 — Automated Employee OnboardingThe moment someone joins the company, this agent automatically provisions every account (Slack, Jira, door access, and more) and sends a welcome message. Zero manual work.Workflow #2 — HR Request TriageNo matter where a request comes in — Slack, Gmail, WhatsApp, or an online form — this workflow normalizes it, deduplicates it, scores it using the Eisenhower Matrix, logs it to Notion or Jira, and only alerts you when something is genuinely urgent.We also go deep on the Personio community node Paul built for n8n, which makes it easy to connect Europe's most widely used HR system to your automation stack.──────────────────────────TIMESTAMPS0:00 - Intro1:21 - Welcome & overview of AI in HR automation1:57 - Demo: Personio trigger node walkthrough2:49 - The #1 HR pain point: employee onboarding3:15 - How the onboarding agent works3:56 - Setting up Slack notifications & welcome messages8:06 - Client intake: mapping a company's tool stack9:43 - On-prem deployments: hospitals & Docker environments12:54 - HR Triage Workflow: handling requests from Slack, Gmail, WhatsApp13:19 - Universal intake normalizer explained14:16 - Eisenhower Matrix for request prioritization15:14 - Full Eisenhower model breakdown23:03 - Building the Personio community node24:04 - Why Paul built it (and where to get it)25:39 - How to connect with Paul26:23 - Enterprise-grade automation vs. vibe coding──────────────────────────#n8n #WorkflowAutomation #HRAutomation #NoCodeGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

🎁 Download the n8n plugin repo → https://go.n8n.io/n8n-ide-pluginStop switching between your IDE and n8n. Build workflows without ever leaving your coding environment.n8n as Code brings n8n directly into Cursor, VS Code, Claude Code, and Open Claude — so you can prompt, build, and iterate on workflows without leaving your editor.In this episode, I sit down with Etienne Lescot, the developer behind n8n as Code, for a fully live demo. We watch him build real workflows inside Claude Code, Open Claude, and Cursor — including a two-way sync where edits in n8n automatically update your local TypeScript files, and vice versa. Zero hallucinations, runs on tiny, cheap LLMs.–––––––––––––––––––––––⏱ TIMESTAMPS0:00 – Intro1:05 – Meet Etienne: the man who built n8n as Code1:54 – Live demo begins: building workflows with Claude Code2:14 – First prompt: Stripe + Postgres workflow3:37 – Switching to Open Cloud: support ticket triage workflow5:38 – How n8n as Code works: built-in tooling & local skills7:02 – Access to 7,000 community templates16:14 – Installation walkthrough: GitHub repo & setup23:13 – Cursor demo: lead nurturing workflow27:51 – Two-way sync between IDE and n8n28:59 – Zero hallucinations: runs on tiny, cheap LLMs–––––––––––––––––––––––🔗 LINKS📦 n8n as Code template: https://go.n8n.io/n8n-ide-plugin–––––––––––––––––––––––#n8n #AIAutomation #WorkflowAutomation #CursorAI #ClaudeCode #nocode #lowcodeGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.

Most businesses want to automate but few know where to start.In this episode, AI engineer and agency owner Dave Ebbelaar walks us through the exact 7-step framework his agency uses to take clients from idea to launch.Whether you're a freelancer, agency owner, or business looking to integrate AI, this episode breaks down a repeatable process that reduces risk, sets the right expectations, and actually delivers ROI.🔑 What you'll learn:→ Why you should use as little AI as possible (even at an AI agency)→ How to identify high-value, low-risk automation opportunities→ Why mapping your current process before building anything is critical→ The difference between deterministic software and AI systems — and why it matters→ How to build safeguards so AI failures don't reach your customers→ What success metrics to track after launch⏱️ Timestamps:0:38 - Overview: 7 Steps to Implementing AI in Business3:01 - Step 1: Discovery8:48 - Step 2: Prioritization & Building the Business Case14:20 - Step 3: Map the As-Is Process19:23 - Step 4: Map the To-Be Process23:57 - Step 5: Prototyping & Proof of Concept28:42 - Step 6: Adding Safeguards & Controls32:37 - Step 7: Launching & Success Metrics37:10 - Managing Client Expectations with AIOne tool Dave recommends for mapping workflows: Business Process Model and Notation (BPMN). If you've never used it, it's worth checking out: https://en.wikipedia.org/wiki/Business_Process_Model_and_Notation#n8n #AIAutomation #WorkflowAutomation #AI #NoCodeGet 30% Off n8n Cloud Starter or Pro Plans! Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.