The problem at team scale is not whether Claude Code works. It is that every engineer uses it differently. One person plans carefully and ships clean diffs. Another pastes a ticket into the terminal and merges whatever compiles. The reviewer sees both in the same PR queue and the review standard drifts down to match the worst contributor. The answer is not another tool. It is one shared operating model the whole team actually uses.
Course objectives
Target audienceSoftware engineers, senior developers, and tech leads inside a team that has been using Claude Code, Cursor, or Copilot unevenly. The course assumes a mix of enthusiasts and skeptics. That mix is the whole point.
Prerequisites
Important informationEvery participant takes a 10-minute online self-assessment before the course. It checks what they already use:
It also checks how they currently handle planning and verification, and what their review process looks like. The assessment routes them to the right track and flags obvious gaps.
Why this matters to our customers:
That lets day one open with "here is what this room already knows and where the shared gaps are" instead of generic material.
Every participant leaves with a versioned template pack checked into a real repository they can open on Monday. The pack is not a slideware deliverable. It is a working set of 10 to 20 files such as:
The pack is co-authored during the course. Participants do not receive it as a gift at the end. They build it, review each other's entries, and commit it. That is what makes it stick. If nobody has owned a particular file by the end of the day, it does not go in the pack.
Two weeks after delivery, the instructor runs a one-hour follow-up with the cohort. The agenda is fixed:
The follow-up is included in the course price. Without it, most of the value walks out the door inside a month.
A short walkthrough of the telemetry: bigger PRs, longer review cycles, higher change failure rates in teams that adopted AI coding without shared standards. Participants self-diagnose their own team against the same pattern.
CLAUDE.md as a living document, not a setup step. What belongs in it, what does not, how to keep it short, and how to stop it from drifting.
Lab:
Decomposing a feature into reviewable units before any agent touches the repo. How to write a brief that a junior engineer and Claude Code can both act on.
Lab:
Safer refactoring patterns. Generating tests that check behavior, not implementation. Debugging with explicit hypotheses.
Lab:
What to look for in an AI-generated diff that a human diff would not have. Verification checklists for business logic, edge cases, error paths, and regressions. When to reject and re-plan instead of asking for fixes.
Lab:
The highest-leverage move at team scale is composition: a PR review workflow that chains a slash command, a CLAUDE.md context, a skill, and a subagent is worth more than any one of those used alone.
We walk through three canonical compositions:
The room builds one end to end for its own stack.
Duration: 1 day
Price: 10 900 NOK
Language: English
Format: Instructor-led classroom training with hands-on exercises
Hva er Claude Code Intermediate?
Claude Code Intermediate er et videregående kurs som bygger på grunnleggende kunnskap og gir deg dypere innsikt i hvordan du bruker Claude Code til mer avanserte utviklingsoppgaver og agentbaserte arbeidsflyter.
Hvem passer kurset for?
Kurset passer for utviklere og tekniske roller som allerede har noe erfaring med Claude Code eller lignende verktøy, og som ønsker å jobbe mer effektivt med AI-assistert utvikling.
Er kurset praktisk rettet?
Ja, kurset er hands-on og inneholder praktiske øvelser og scenarier hvor du jobber direkte med Claude Code i realistiske utviklingsoppgaver.
Hva er forskjellen på Beginner og Intermediate?
Beginner-kurset fokuserer på grunnleggende funksjoner og oppstart, mens Intermediate går mer i dybden på arbeidsflyt, automatisering, strukturering av oppgaver og mer avansert bruk av verktøyet.
Hva lærer jeg som er nyttig i praksis?
Du lærer hvordan du kan bruke Claude Code mer effektivt i utviklingsprosesser, automatisere oppgaver, håndtere større kodebaser og jobbe mer strukturert med agentbaserte løsninger.
