AI Classification Without the Cloud — the Ticket Workflow Gets a Brain

Getting Started with n8n

A series on n8n as a self-hosted workflow and agent platform — from the first container to a production-ready pipeline with AI classification and SAP integration.

In May 2026, SAP took a strategic stake in n8n and embedded the platform into Joule Studio. Mercedes-Benz is rolling out n8n as a global automation platform and cites digital sovereignty as a key selection criterion. This series takes both events as a starting point and works through n8n from the ground up — self-hosting with Docker, the item model, AI agent nodes, error handling, observability, and the bridge into the SAP world. The demo project is a triage system for support tickets. Code lives openly on Codeberg, with a tag per article to follow along. Nine articles plus a prologue.

  1. 0

    Why n8n, why now — Prologue to the Getting-Started Series

    SAP has taken a strategic stake in n8n and embedded it in Joule Studio. Mercedes-Benz is rolling out the platform globally. A prologue to the n8n getting-started series.
    18. May 2026
  2. 1

    n8n in Overview — Architecture, Item Model, and Demo Repo

    What n8n actually is under the hood: editor, execution engine, task runners, workflows as JSON. Plus the item array as the central data model and where n8n fits in the integration landscape.
    20. May 2026
  3. 2

    Self-Hosting with Docker Compose — n8n, Postgres, and Caddy

    Self-hosting n8n in a production-grade setup: Docker Compose, Postgres instead of SQLite, Caddy with auto-HTTPS, persistent volumes, and the environment variables that actually matter.
    21. May 2026
  4. 3

    Test Data, Because Real Data Is Off the Table

    Why a real ticket dataset has no place in a public repo, and how a hybrid generator using local models and Claude produces realistic test data with a reproducible distribution.
    22. May 2026
  5. 4

    Nodes, Expressions, and the First Workflow Without AI

    Building a rule-based ticket classifier in n8n: the item model in practice, writing expressions correctly, choosing between Set and Code nodes — and where the classifier predictably fails.
    26. May 2026
  6. 5

    Webhooks, HTTP, and Credentials — the Production Entrance

    How an n8n workflow gets an authenticated webhook endpoint, how credentials are stored securely, and how classifier logic is extracted into a sub-workflow.
    27. May 2026
  7. 6

    AI Classification Without the Cloud — the Ticket Workflow Gets a Brain

    How an n8n workflow classifies tickets with a local language model: structured output, two backends without a cloud key, deterministic language detection, and a benchmark that exposes its own weakness.
    1. Jun 2026