Report a bug

What went wrong?

n8n AI Automations — AI Academy

AI Academy/Courses/n8n AI Automations

⌘K

UK Sign in Sign up

IntermediateИнженерия

n8n AI Automations

Practical course on building AI automations in n8n: integrating ChatGPT, Claude, and Gemini via HTTP nodes and built-in AI nodes. Creating AI agents in n8n with memory, tools, and webhook triggers. Real business workflows: email processing, Telegram bots, CRM integrations, and content automation.

4modules

12lessons

385 mintotal time

Entrepreneurs and developers automating business processes with AIaudience

Progress

0%0 / 12 lessons

Sign in to save your progress.

Module 1

n8n + AI Foundations

Installing n8n, connecting AI providers, built-in LLM nodes, and direct HTTP calls to any AI API.

Installing n8n and your first AI workflow

Self-hosted (Docker) vs n8n.cloud, connecting OpenAI/Anthropic/Google credentials, a first HTTP Request → OpenAI → Slack workflow, and the n8n data model (items, JSON).

n8n's built-in LLM nodes

Chat Model (OpenAI, Anthropic, Google), Basic LLM Chain, Question & Answer Chain, Text Classifier, Summarize — when to use each vs raw HTTP.

Any AI API via HTTP Request

Headers, body, auth, parsing JSON, error handling via IF, retry logic — calling any AI API without a built-in node.

Module 2

AI Agents in n8n

The AI Agent node, agent types, wiring memory and tools, multi-user sessions.

The AI Agent node

Agent types (Tools Agent, Conversational Agent), wiring memory (Window Buffer, Postgres), tools (Calculator, HTTP, SerpAPI, sub-workflow).

Agent memory: types and sessions

Simple Memory vs Window Buffer vs Postgres Chat Memory, session IDs for multi-user, clearing memory via webhook, size limits.

Built-in tools (Wikipedia, SerpAPI, Code), custom tools via sub-workflows, the HTTP tool for external APIs, tool selection by the agent.

Module 3

Real Business Workflows

Ready scenarios: AI email processing, a Telegram bot, content automation.

AI email processing

Gmail/IMAP trigger → AI classification → draft reply → human approval → send. Structured data extraction with Claude, attachments.

Telegram bot with AI Agent

Telegram Trigger, session-based conversation with an AI Agent, commands (/start, /help), formatted messages, voice transcription via Whisper.

Content automation

RSS → AI summarization → LinkedIn/Twitter/Telegram post generation → scheduled publish. Batching via SplitInBatches, rate limiting.

Module 4

Production & Advanced Patterns

Webhook triggers, RAG inside n8n, error handling, monitoring, and management via the API.

Webhook patterns for AI

Webhook as an AI trigger, authentication (Header Auth, HMAC), synchronous vs async response, queueing via Wait.

Full RAG inside n8n

Supabase Vector Store + Embeddings in n8n, a document ingestion workflow, a query workflow (embed → vector search → LLM), a full RAG pipeline.

Production: errors, monitoring, versioning

Error Trigger and error workflows, monitoring executions, environment variables, workflow version control, the n8n API for management.

AAI AcademyEN Start learningCatalog

Overview

AI Academy Progress Achievements Leaderboard Insights Notes Notifications Team API Pricing Settings

Learning

Tracks8 Courses51

Libraries

Prompts30 Workflows12 Tools22 Compare Blog

Updated · May 14, 2026