Claude Code in April 2026 is a layered system, not a prompt box. Most teams only use one or two of its layers. The cost of that is not obvious: it looks like productivity, but it shows up later as review debt, inconsistent enforcement, and invisible changes that only the author understands. This course teaches the design decisions behind each layer and how to wire them together so speed does not turn into breakage.
Course objectives
Target audienceSenior engineers, staff and principal engineers, tech leads, platform and developer-experience teams, and internal AI champions. The course assumes participants are not just power users. They are the people other engineers come to with questions.
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.
We cover:
Participants receive the Claude Code Feature Matrix on day one and use it throughout the course.
|
Primitive |
Invocation |
Persistence |
Best for |
|
Slash commands |
User types /name |
File in .claude/commands |
Named repeatable prompts |
|
Skills |
Auto or manual |
File in .claude/skills |
Procedures with supporting scripts |
|
CLAUDE.md |
Auto-loaded |
In repo, checked into git |
Durable team policy and context |
|
Hooks |
Event-triggered |
In settings or repo |
Deterministic guardrails |
|
Subagents |
Delegated by main agent |
Spawned per task |
Fire-and-forget research or work |
| Agent Teams |
Orchestrated by lead |
Session-scoped |
Peer-to-peer parallel collaboration |
| Checkpoints |
Auto on each prompt |
Session-scoped |
Safe A/B experimentation and rewind |
| MCP servers |
Tool calls |
Configured once |
External context and tool access |
| Plugins |
One-command install |
Bundled assets |
Packaging everything above |
Where external context actually changes decisions, where it only adds latency and attack surface, and which MCP servers to trust, sandbox, or human-gate.
Lab:
Turning repeated prompts into versioned, reviewable skills. Packaging related skills, commands, hooks, and subagents as a plugin so a new hire inherits the team's conventions on day one.
Lab:
Subagents and agent teams look similar but solve different problems. We cover when each one earns its token cost and when both are just agent theater.
Lab:
Deterministic control for the things a prompt cannot reliably guarantee.
We cover:
Lab:
Participants design a 90-day rollout for their team. The rollout must include at least one headless-mode pattern, with Claude Code running inside a CI pipeline for automated review, release notes, triage, or documentation.
Duration: 1 day
Price: 10 900 NOK
Language: English
Format: Instructor-led classroom training with hands-on exercises
Hva er Claude Code Advanced?
Claude Code Advanced er et avansert kurs som fokuserer på å bruke Claude Code til komplekse utviklingsoppgaver, automatisering og agentbaserte systemer i større prosjekter.
Hvem passer kurset for?
Kurset passer for erfarne utviklere og tekniske roller som allerede har jobbet med Claude Code eller lignende verktøy, og som ønsker å ta bruken videre til et mer avansert nivå.
Er kurset praktisk rettet?
Ja, kurset er hands-on og inkluderer avanserte øvelser hvor du jobber med komplekse scenarier og agentbaserte arbeidsflyter.
Hva er forskjellen på Intermediate og Advanced?
Intermediate fokuserer på struktur og effektiv bruk av verktøyet, mens Advanced går dypere inn i arkitektur, automatisering, orkestrering av agenter og optimalisering av utviklingsprosesser.
Hva lærer jeg som er nyttig i praksis?
Du lærer hvordan du kan bygge mer avanserte og skalerbare arbeidsflyter, bruke Claude Code til komplekse utviklingsoppgaver, og optimalisere både kvalitet, sikkerhet og effektivitet i utviklingsprosesser.
