Claude Code Beginners

Most developers already have Claude Code installed by the time they take a course like this. What they usually do not have is a repeatable loop. They prompt, they get a 400-line diff, they spot-check it, they merge, and the reviewer inherits the problem. First-week Claude Code usage tends to produce more reviewer work than it saves.

This course replaces that pattern with a plan-first loop:

  • read the repo
  • write a spec
  • get a plan
  • accept or reject the plan
  • generate in small bounded steps
  • verify with tests
  • commit

It is the minimum viable habit for someone about to do real work with an agent on a real codebase.

Course objectives

  • Explain where Claude Code fits in their existing workflow, and where it does not
  • Read a repo well enough that their first prompt has the context the agent actually needs
  • Turn a ticket into a short written spec with constraints and acceptance criteria before any code is generated
  • Use plan mode to keep changes small, reviewable, and resettable when output drifts
  • Turn a repeated loop into a named slash command instead of retyping the same prompt
  • Debug Claude Code's output with explicit hypotheses instead of re-prompting until something passes
  • Decide, for a given task, whether to delegate to Claude Code, review carefully, or keep it fully human-owned

Target audience

Developers and senior developers joining a team that has standardized on Claude Code, or evaluating it seriously for the first time. Engineering managers who want to understand the loop their team is about to adopt are welcome, but this is a hands-on day with real labs.

Prerequisites

  • Has shipped code through a Git workflow before
  • Comfortable in a terminal or an IDE terminal
  • Has Claude Code installed and authenticated before the course starts
  • Has completed the pre-course self-assessment

Important information

Pre-Course Self-Assessment:

Every participant takes a 10-minute online self-assessment before the course. This lets day one open with "here is what this room already knows and where the shared gaps are" instead of generic material.

Take-Home Template Pack:

Every participant leaves with a versioned template pack checked into a real repository. The pack is not a slideware deliverable. It is a working set of 10 to 20 files.

30- Day Follow-Up

Two weeks after delivery, the instructor runs a one-hour follow-up with the cohort.

About the instructors: Rogier Muller & Vasilis Tsolis

Rogier Muller  is CTO of BlueMonks Group, an Amsterdam-based fintech compliance company, and co-founder of several companies. He`s a lifelong coder who moved early into AI-assisted software development. Today, he is the only person in the world to combine official ambassador roles across the three leading agentic engineering platforms: Cursor, Claude Code, and Codex. Rogier has hosted numerous events worldwide and works closely with engineering teams, founders, and AI tooling companies on the practical adoption of agentic software development. His specific expertise is using agentic engineering in highly regulated environments, including but not limited to fintech, financial services, KYC/CDD, AML, GDPR, AFM-supervised contexts, auditability, data isolation, and compliance-heavy software delivery.

Vasilis Tsolis is a pioneer in document intelligence and agentic coding helping teams to change how they work across industries. He is an official Ambassador for Cursor, OpenAI Codex and n8n. He is the partner of Cognitiv+, an AI consultancy and software factory that helps organisations practically implement and adopt AI with enterprise confidence. He has co-founded several companies and trains development teams across the US and EU on AI-assisted coding, with a consistent focus on integrating it into real workflows without losing control of the codebase. Background: engineering and law, twenty years across AI, construction, energy, and tech.  Vasilis has worked with JPMorgan, Intel, PwC, and others along the way.

Module 1 - The First-Week Failure Pattern

We open with the reason most people under-deliver with Claude Code in week one: no plan, no spec, no verification. Short live walkthrough of the weak version of the loop and the strong version, on the same ticket, side by side.

Module 2 - Reading The Repo Before Prompting

Structure, conventions, hot files, existing patterns. How to spend five minutes on the repo so the agent spends forty minutes doing the right thing.

Lab:

  • Participants map their own repo, or a provided one, into a short context note

Module 3 - Writing A Spec The Agent Can Act On

Turning a ticket into constraints and acceptance criteria. Comparing weak prompts to spec-driven prompts on the same task.

Lab:

  • Participants rewrite three of their own recent prompts

Module 4 - Plan Mode And Small Diffs

Using plan mode to force a design conversation before any file is touched. Rejecting and resetting when the plan drifts. Keeping each change small enough that a reviewer can reason about it in under ten minutes.

Lab:

  • A bounded feature implemented in three reviewable commits

Module 5 - Slash Commands: Naming Your Loop

The moment a developer writes the same spec twice, it should be a slash command. We introduce slash commands as the bridge from ad-hoc prompting to named, reviewable, version-controlled workflows.

Lab:

  • Each participant turns one of their rewritten prompts from Module 3 into a working /command checked into .claude/commands/

Module 6 - Verify, Don't Hope

Running tests, checking assumptions, reading the diff the reviewer will read. Debugging with a hypothesis instead of re-prompting.

Lab:

  • A seeded bug that will not be caught by the happy-path test

We close the day with the delegate, review, own decision model: which tasks go to Claude Code, which get reviewed carefully, and which stay human end to end.

What Participants Leave With

  • A one-page Claude Code Loop cheat sheet
  • A starter CLAUDE.md template they can drop into their next project
  • Three working slash commands they authored during the course, checked into a repo
  • A decision table for delegate, review, own, tailored to the languages and stacks in the room

Practical information

Duration: 1 day
Price: 10 900 NOK
Language: English
Format: Instructor-led classroom training with hands-on exercises

FAQ

Hva er Claude Code Beginners?
Claude Code Beginners er et introduksjonskurs som gir deg en praktisk innføring i Claude Code og hvordan du kan bruke det til å jobbe med kode og automatisere oppgaver.

Trenger jeg erfaring med AI eller LLM-er?
Nei, men du bør ha erfaring som utvikler og grunnleggende forståelse for programmering.

Er kurset praktisk rettet?
Ja, kurset er hands-on og inneholder øvelser og praktiske eksempler gjennom hele opplæringen.

Hva lærer jeg i løpet av kurset?
Du lærer blant annet å bruke Claude Code til å utforske kode, jobbe med kontekst og minne, bruke kommandoer og bygge enkle agentbaserte arbeidsflyter.

Hvem passer kurset for?
Kurset passer for utviklere og tekniske roller som ønsker å komme i gang med AI-assistert utvikling og agentbaserte verktøy.

Other relevant courses

Other subject areas

Andre relevante kurs

React 19 (Including NextJS) (Hands-on)
22. juni
5 dager
Classroom Virtual
React Advanced (Hands-on)
23. september
3 dager
Classroom Virtual
Svelte & Svelte Kit
7. oktober
3 dager
Classroom Virtual
Blazor - Web Applications with C#
18. august
4 dager
Classroom Virtual