AI training for companies: workshops that end with automations that run.
I run AI training for teams. In the workshop, people build AI agents and n8n automations on their own company's processes, working alongside an AI assistant. They leave with workflows that run and the skill to build the next ones. What I teach is the method I use on client implementations every day.
- 66people in my hands-on n8n workshop with an AI assistant at AI Summit Poland 2026
- since May 2026weekly team training at an e-commerce client: finance, warehouse and sales now build on their own
- 190,000+users of n8n-mcp, the tool participants build workflows with
Most AI training ends with a tour of tools. People go back to their desks with notes and nothing that runs, and a month later few of them remember what was on the slides.
My training starts from your processes. Before the workshop we pick ideas that can be built in a day, and I prepare reference versions of them on your n8n. In the workshop, participants build them themselves with an AI assistant connected to n8n through n8n-mcp, with the reference version as the benchmark. Critical processes, such as financial reconciliation, stay out of the workshop: I implement those myself.
Training formats
Hands-on workshops with n8n and an AI assistant
Groups of 10–12, two sessions of four hours each, at your office, on your own n8n instance. In the first session participants build a workflow with an AI assistant. In the second they take it from working to reliable: edge cases, error handling, security and a handover checklist. Preparing two workflows from your own ideas is included.
AI champions programme
For companies building an internal automation team. The people who own each idea describe their process in a short conversation with an AI assistant, which turns it into a brief in one shared format. In a selection workshop we place the ideas on an impact and effort map and agree what you build in the workshops, what I implement and what waits. Then come the workshops and ongoing support.
Training combined with an n8n implementation
Together with your IT team I set up n8n on your infrastructure, connect the data from the systems you use and document every integration so a participant can paste that documentation into their AI assistant and build on the same data. Critical processes with many data sources or financial reconciliation I build and test myself, alongside the workshops.
Weekly sessions for the team
One hour a week with the people who automate inside their departments: reviewing what they built, clearing blockers, picking the next ideas. Plus monitoring of employee-built workflows, so none of them overloads or breaks the instance.
AI workshop for leadership
Half a day or a full day for the board and managers: what AI can do today, where the line runs in your processes and where to start.
Who this is for
- Companies that have named internal AI champions and want them building things, not collecting webinar certificates.
- Teams that already run n8n, or are rolling it out, and need a way of working that keeps quality up once people outside IT start building automations.
- Operations, finance, sales and marketing departments doing repetitive work on data spread across several systems.
- Organisations where IT has to approve the environment, access and rules before anyone starts building.
How I run it
- 01Briefs and idea selection
I collect ideas from process owners in one format and pick, together with you, the ones that can be built in a day. Ideas too complex for a workshop I mark as implementation candidates, or as things not worth doing in n8n.
- 02Environment ready in advance
I agree access and rules with IT. Before the first session every participant has an account on your n8n, access to the systems behind the chosen ideas and an AI assistant connected to n8n, checked with a connection test. Nobody spends workshop time waiting for access.
- 03Workshops on your processes
Participants build the chosen ideas end to end on agreed data, with the reference version as the benchmark. We finish with a handover checklist: error handling, edge cases, security.
- 04Support after the workshops
Weekly sessions and reviews of what the team builds next. Ideas that need a production implementation I quote separately, before any work starts.
What this is based on
I teach on the tool I implement with every day. At an e-commerce client, team training grew out of my own implementations, and today the team builds automations and agents on its own.
Over 200 workflows on one platform — marketplace automation across 6 countries, agentic product research, custom microservices and an internal automation team trained to work independently.
Read the case studyThe tool that lets AI agents build working n8n automations — 23,000+ GitHub stars, 190,000+ users and 1.9M+ workflows built, including at Deutsche Telekom, PayPal, Mercado Libre, MIT and NYU. Built entirely agentically.
Read the case studyGuides
Three guides to start with: connecting an AI assistant to n8n, giving it n8n skills, and how the n8n AI Agent works.
How do you connect Claude Code to n8n through MCP, and what can the agent do then?
Claude Code connects to n8n through the n8n-mcp MCP server: one terminal command adds the server, and the agent gets documentation for every n8n node, configuration validation and workflow operations on your instance. From then on it can build, fix and test a workflow from a description in plain language. More than 190,000 people use n8n-mcp, and its telemetry shows agents spend four times more calls reading and checking than writing.
Read the guideHow do you install n8n-skills, and why does an AI agent need skills for n8n?
n8n-skills is a set of 14 skills plus a skill router and a hooks layer that teach an AI agent the right patterns for building n8n workflows through the n8n-mcp server. You install it with one command in Claude Code, as zip files in Claude.ai and ChatGPT, or as a plugin in Codex. An agent without skills guesses at syntax and puts instructions in the wrong place; an agent with skills sticks to proven patterns and conventions.
Read the guideWhat is the n8n AI Agent and how does it work?
The n8n AI Agent is a node in which a language model receives instructions (a system message) and a set of tools, then decides on its own which tools to call to complete a task. Without tools it is just a chat. With tools, most often sub-workflows, the agent can read a document, check data in a spreadsheet and make a judgement call no plain rule can handle. Since August 2026 n8n also has a separate Agents category: agents with their own memory, channels and skills that live outside a single workflow.
Read the guideCommon questions
- How much does AI training for a company cost?
- I quote after a short call, as one price for the whole agreed scope. It depends on the number of groups, the number of workflows to prepare and whether the training comes with an n8n implementation. Preparing reference workflows from your own ideas is always included.
- Do participants need to know n8n?
- The basics are enough. Before the workshop every participant completes the free N8N101 course in n8n Academy. The workshop does not repeat the basics; we go straight to building.
- Which n8n does the training run on?
- Yours: self-hosted on your infrastructure, or n8n Cloud. If you do not have it yet, I set it up with your IT team before the workshop.
- Which AI assistant do we work with?
- Claude Code or Codex, connected to n8n through n8n-mcp, the tool I built. The choice depends on what your IT allows and which licences participants have.
- What do we have after the training?
- Working workflows built on your processes, their documentation, a handover checklist and a summary for whoever owns the programme: what we built and which ideas are worth taking further.
- Will we build a critical process in the workshop?
- No. A process whose result has to be right to the cent, or that joins many data sources, is not something to build in a day at a workshop. I implement those myself, with tests and a trial run, and the team learns on simpler ideas using the same data.
- Do you train individuals?
- No. I train teams inside companies. For anyone who wants to start on their own there is the free course "Your first AI agent" at course.aiadvisors.pl.