Skip to content

Trainings

Databases and pipelines sooner, built by AI agents your platform team steers.

AI agent training for platform, DevOps and SRE teams: two hands-on days on your own infrastructure code.

  • Steffen Clemens
  • Jost Künzel
  • Nils Eckelt
  • Luis Fernando De La Torre Delgado
Get an offer

EUR 1,500 per participant

  • Two days
  • remote or on site
  • handpicked trainer
I read the summary of the training and I'm really happy with the content. On top of that, the training and you as the trainer went down very well with the participants. That says a lot, because in my view this was our toughest group.
Alexander Heusingfeld (opens in a new tab)
Head of Platforms & Lifecycle Management Vorwerk

What the training does

In two days, Agentic Engineering for DevOps and Platform Teams gives your platform team one shared way to hand its routine work to agents: plan reviews, provider upgrades, pipeline repairs, drift and incident triage. Every apply stays behind your team's own approval.

Platform work has its own risks. Your team keeps infrastructure, clusters, networks and pipelines running, and a wrong change hits running systems. Our trainers work on cloud platforms, Kubernetes and Terraform themselves. They start with how agents work, then set the guardrails first: what the agent may read, what it may change, and which credentials stay with your team. Day two runs on your team's real tickets.

Who it's for

Two days for platform, DevOps and SRE teams on your own infrastructure code.

Participants work daily with infrastructure as code, Kubernetes or pipelines, at any level of agent experience.

Teams that build applications on your platform pick Agentic Engineering for Developers and QA.

What your team takes away

  • Project rules and permission settings in your own infrastructure repository, and a first skill for a recurring chore
  • A credentials setup that keeps write access to shared environments out of agent sessions
  • A first change from your backlog as a pull request with its plan, ready for your normal review
  • The training handout for every participant
  • An individual certificate of attendance for every participant

What changes

Less of the repetitive work lands on your engineers: provider upgrades, red pipelines and drift reports start as a pull request with an explanation. Every agent works within rules your team wrote down, so nobody has to guess what an agent may touch. And your runbooks become skills the agent follows when your on-call asks it to investigate.

What the days cover

Day 1: AI agents on your own infrastructure code
  • Framing: the team names the toil it wants to hand to agents and what stays with people.
  • How agents work: LLMs, tokens and the agent loop, then the agent explains your own Terraform, read-only.
  • Project memory for infrastructure: the team writes the rules its repo needs: environments, state, naming, and the commands that stay off limits.
  • Permissions and blast radius: the team blocks apply and destroy, keeps write credentials out of the session and tries to break its own guardrails.
  • Context for plans, logs and CLIs: the agent reads long plans and logs through filters and works through the CLIs your team already uses.
Day 2: Your real work, through a safe change loop
  • Skills and hooks for Ops: the team builds a plan-review skill and a command for one recurring chore.
  • The infrastructure change loop: a real ticket from your backlog goes from change to plan to pull request, and the apply stays behind your team's approval.
  • Pipelines and drift: the agent repairs one of your team's failing pipelines and explains a drift report.
  • Incidents and runbooks: the agent investigates one of your recent incidents read-only, and one runbook becomes a skill.
  • The platform for everyone's agents: the team decides what its platform gives other teams' agents and what it refuses, and takes its setup into next week.

How it runs

  • On your infrastructure code

    On day one the agent explains your own code, without write access. Day two runs on real tickets from your backlog, and many teams bring a real change into their normal review before the training ends.

  • Guardrails before speed

    During the training, write credentials for shared environments stay with your team, and applies stay with your pipeline and your approval rules.

  • Mechanics before magic

    First how the agent works, then what to do with it. The practice carries over to whatever your company standardises on next.

  • Mentoring as your team applies it

    We stay with your team while it puts what it learned to the test in real work. Sessions follow the team's progress on real work.

  • Lifetime access to our community

    Free for every participant: people from other teams share what works in the hackers&wizards community.

Runs in Claude Code, Codex, GitHub Copilot, Gemini CLI or Cursor.

Trainings by tool

Who delivers it

Delivered by one of our more than 70 trainers. For each group, we propose a trainer based on technical fit, language and seniority, and on whether they will get on with that group. In our experience, the personal fit matters most. You accept or decline, then you get to know them and we prepare the training together.

A selection from our trainer pool.

AboutAll trainers

What it goes with

Your application teams learn the same vocabulary in Agentic Engineering for Developers and QA, so the agents on both sides of the platform follow rules that match.

What clients say

What clients say about our trainings

We brought in hackers&wizards to help our engineering team get under the hood of agentic tooling, and the session delivered real value. The content was technically deep without being abstract, and the team left with practical ideas they could immediately start exploring. For a regulated environment like ours, the balance of innovation and pragmatism was particularly welcome. A genuinely worthwhile investment of the team's time.
Jim Holmes (opens in a new tab)
VP Technology Skin Analytics
The workshop was inspiring and pushed me to think big. The end-to-end migration pipeline example really stayed with me. We're using Claude Code far more aggressively now.
Dr. Jan Henrik Ziegeldorf (opens in a new tab)
CTO & Co-Founder aedifion

Questions before booking

Who is Agentic Engineering for DevOps and Platform Teams for?

DevOps, SRE and platform engineers who run infrastructure, pipelines and operations.

How long does it take, and where?

Two days, remote or on site, handpicked trainer

What does it cost?

EUR 1,500 per participant. Team training, EUR 15,000 at most for the two days: up to 12 people attend, and you pay for 10 at most. Net, plus VAT. On site, plus travel at cost.

A team of fewer than eight pays the same EUR 750 per participant and day, or brings a neighbouring team along.

Does the agent get access to production?

Production stays behind your pipeline and your approval rules. In the training the agent reads your code and writes changes, and every apply to a shared environment runs through your pipeline. Until you approve real plans and logs for the model, the exercises use prepared ones. In the preparation call we settle with you which model route, retention and redaction apply, and who signs that off.

We use OpenTofu instead of Terraform, or mostly Kubernetes. Does it fit?

Yes. OpenTofu works like Terraform in every exercise, and Kubernetes teams run the change loop with manifests, Helm and dry-runs. For Pulumi or Ansible, ask us first: in the preparation call we check whether a trainer has run your stack.

Remote or in person?

Both. Remote runs on your Microsoft Teams or Google Meet, cameras on, in a shared repository. On site, we come to you and bill travel and accommodation at cost.

Which tools do you teach?

Our engineering, product and leadership trainings run in the coding agent your team already uses: Claude Code, Codex, GitHub Copilot, Gemini CLI or Cursor. We have delivered each of these trainings in every one of these agents. Agentic Workflows for Business Teams uses a desktop app: Claude, ChatGPT or Microsoft Copilot.

The instruction files, settings and approval modes differ by agent. We set them up with your team on day one. The practice is Agentic Engineering, and it carries over to whatever your company standardises on next.

No coding agent yet? We bring one that fits your team. Licences are on you, whether you supply them or we do.

How quickly can we start?

Plan on about four weeks from the order to the first training day. We agree the date with you, and your team's calendar usually decides it. It can go faster: in 2026, our quickest start came 11 days after the order.

Is funding available?

German companies may qualify for support under the Qualifizierungs­chancen­gesetz, depending on the company and the participants. We look at the route with you.

Not sure where to start? Take the self-check