How-To
Step-by-step guides with video, screenshots and code. Set up your tools, connect integrations, fix errors and ship faster. Search or filter by category, then follow each guide one step at a time.
New guides in your inbox
Fresh step-by-step how-to guides as we publish them. One email a week, no more.
How to Self-Host n8n with Docker for AI Workflows
Run your own n8n instance in Docker with persistent storage and an encryption key so AI workflows and credentials survive restarts.
How to Add OpenAI Credentials to n8n
Create an OpenAI API key, store it as a reusable credential in n8n, and verify it with a one-node test before building real AI workflows.
How to Build an n8n Workflow That Summarizes New Emails with AI
Trigger on incoming Gmail messages, summarize each one with an LLM, and post the digest to a channel so you stop reading low-value email in full.
How to Build a RAG Chatbot Over Your Docs in n8n
Embed your documents into a vector store, then answer questions against them with an AI Agent so replies are grounded in your own content.
How to Auto-Classify and Route Support Tickets with AI in n8n
Use an LLM to tag incoming tickets by category and urgency, then branch the workflow to route each one to the right team automatically.
How to Schedule Daily AI Content Generation in n8n
Use a Schedule Trigger to generate a draft post every morning with an LLM and drop it into a doc or sheet for review.
How to Build an AI Agent with Tools in n8n
Set up the AI Agent node with a chat model, memory, and custom tools so it can decide when to call APIs instead of just chatting.
How to Extract Structured Data from PDFs with AI in n8n
Read a PDF, pass its text to an LLM with an output schema, and turn unstructured invoices or forms into clean rows in a spreadsheet.
How to Connect Anthropic Claude as the Model in n8n Workflows
Add an Anthropic credential and use a Claude chat model in n8n nodes and agents so you can compare or switch providers freely.
How to Add Error Handling and Retries to n8n AI Workflows
Protect AI workflows from rate limits and flaky responses with node retries, an error workflow, and alerts so failures never go silent.
How to Transcribe and Summarize Audio with AI in n8n
Send an audio file to a speech-to-text model, then summarize the transcript with an LLM to turn meetings and voice notes into action items.
How to Connect AI to Chat Apps Without Code Using n8n
Wire a chat webhook to an AI node and a reply node in n8n to auto-answer messages, no code required.
How to Trigger an n8n AI Agent from a Webhook Node
Expose an n8n webhook, feed the request into the built-in AI Agent node, and return the model reply as the HTTP response.
How to Verify Webhook Signatures Before Calling an AI Model
Stop strangers from running up your AI bill by checking an HMAC signature in n8n or Make before any model call.
How to Answer a Webhook Instantly While AI Runs in the Background in n8n
Acknowledge the caller in milliseconds, then process a slow AI task asynchronously so the request never times out.
How to Build a Slack Slash Command AI Bot with an n8n Webhook
Wire a Slack slash command to an n8n webhook, run the text through a model, and post the answer back in channel.
How to Cap AI Spend on a Webhook Across Zapier, Make, and n8n
Add per-day request counters and short prompts so a busy webhook cannot blow past your AI budget.
How to sync AI-extracted tasks from email to your calendar with n8n
Self-host an n8n workflow that reads email, extracts deadlines with AI, and creates calendar events, all under your own control.
How to Extract Structured Data from PDFs with n8n
Read a PDF in n8n, send the text to an LLM with a fixed schema, and write clean JSON rows to Google Sheets or a database.
How to Build an AI Messaging / Chatbot Automation (No Code)
Wire a chat trigger to an AI model and reply automatically, using n8n or Make, with no code and one short prompt.
Dify vs n8n: Which Should You Use for AI Workflows
An honest comparison of Dify and n8n: Dify is an LLM app builder with a hosted UI and API, n8n is general automation with hundreds of integrations. When to pick each, and how to combine them.