⚙
Hardware Plan
What to buy, and when
Your iMac M1 with 8GB RAM is sufficient for all four phases of this plan. Hardware upgrades are driven by workflow need, not enthusiasm. Here's the honest timeline.
Now — Before Week 1
LaCie Rugged as overflow storage
Move Photos library and large files onto it to free up internal SSD space. The LaCie is a spinning HDD — use it for storage only, not for running code projects. Cost: €0, you already own it.
Phases 1–3 · Weeks 1–14
No new hardware needed
Your iMac handles Python scripts, VS Code, Git, and Claude Code comfortably. 8GB RAM is tight but workable for the project scope in this plan. The bottleneck will be disk space, not compute — hence freeing up space now.
Phase 4 · Weeks 15–20
Optional: external SSD (~€80–120)
When running Flask server + database + Claude Code + browser simultaneously, 8GB RAM will feel constrained. An external SSD (Samsung T7 or similar, USB-C) gives you fast overflow storage for project files if your internal drive fills up again. Not mandatory — evaluate when you get there.
Phase 4+ · Month 5 onward
Mac mini M5 — when it launches
A dedicated always-on machine becomes worthwhile when you have tools you trust running unattended overnight. The M5 Mac mini is expected soon (low stock on M4 suggests imminent refresh). Wait for it. Spec: 16GB RAM minimum, 256GB SSD. Connects to your existing display. Budget: €800–1,000. This is the machine you SSH into from your laptop or phone to run agents while you're with clients.
Not needed for your goals
Cloud VMs, Docker, NAS, extra RAM
These solve problems you won't have at this scale. Advisory automation is low-volume and reasoning-heavy — a Mac mini running Claude Code Routines handles it. Don't buy infrastructure speculatively.
Goal: reach genuine fluency — enough to evaluate, direct, and modify AI-built tools, and to advise clients from experience rather than speculation.
Honest caveat: Claude Code is a multiplier. Used too early it produces code you can't evaluate. The first 6 weeks feel slow. That's the foundation. Don't skip it.
Ph 1
Python Foundations
Weeks 1–6 · No Claude Code yet
Building the evaluation threshold. Until you can read code and roughly assess whether it's right, Claude Code is a liability, not an asset.
Rule: No Claude Code in this phase. Use Claude (this chat) to explain concepts and debug errors. Do not use it to write code for you.
Daily structure
- Weekdays (1 hr): 20 min read/watch · 30 min type and run code yourself — no copy-paste · 10 min break something and fix it
- Weekends (3 hrs/day): Sat: build a small project from the week's concepts · Sun: refactor it, add one new feature
Spec before code — even now. Every project from the Phase 1 briefing summariser onward starts with a 1-page written spec: what it does, what it doesn't, what success looks like. You're writing the code yourself at this stage so it feels redundant. The point is to build the muscle before Phase 3, where spec quality becomes the bottleneck for everything Claude Code produces.
Curriculum
Wk 1–2The basics
- Variables, strings, integers, booleans
- Print statements and f-strings
- If / elif / else
- Lists and loops (for, while)
Wk 3–4Functions & files
- Writing and calling functions
- Parameters and return values
- Reading and writing text files
- Reading CSV files with the csv module
Wk 5–6Real data & APIs
- Dictionaries — the most important data structure for your goals
- JSON — what it is, reading and writing it
- The requests library — calling an external API
- Error handling with try/except
Phase 1 Project
Client briefing summariser
A script that reads a CSV of client names, industries, and notes, then outputs a formatted text summary for each client. Run it in your terminal. Show it to someone. If they find it useful, you've passed.
specPythonfile I/OCSVreal data
📺 Nick's course — not yet
Skip Nick's course in Phase 1
His 4-hour course assumes you can already read code. Watching it now would be like reading a navigation manual before you've learned to drive. Come back to it in Phase 3.
Ph 2
Shell, Git & Environment
Weeks 7–8 · Install Claude Code
Not programming — infrastructure. The scaffolding every real project needs.
3 daysShell essentials
- pwd — where am I?
- ls — what's here?
- cd — move around
- mkdir — create a folder
- cp / mv / rm — copy, move, delete
4 daysGit fundamentals
Mental model: Git takes snapshots, not deltas. Every commit is a full save point — your undo button when Claude Code goes wrong.
Pro Git Ch. 1–3 (free at git-scm.com/book)
- git init · git add . · git commit -m "msg"
- git log · git branch · git checkout
Pro Git Ch. 1–3 (free at git-scm.com/book)
1 dayFull environment setup
Install in this order:
- Homebrew: brew.sh
- Python 3: brew install python
- VS Code + Python extension (code.visualstudio.com)
- Git: brew install git
- Node.js: brew install node
- Claude Code: npm install -g @anthropic-ai/claude-code
📺 Nick's course — Week 8
4-Hour Course: Chapters 1–4 (first ~30 min)
Watch after you've installed Claude Code. Nick walks through setup, what an IDE is, and how to run Claude Code in the terminal. Seeing it done by someone fluent reinforces what you've just installed yourself. Skip his Antigravity IDE sections — use VS Code instead.
setupIDE overviewterminal basics
Ph 3
First Claude Code Projects
Weeks 9–14 · Directed building
You direct, Claude Code executes. The bottleneck in working with Claude Code isn't writing code — it's managing what context Claude has when it writes. The operating rule: before accepting any file it produces, read it. If you can't explain a section, ask before moving on.
The core loop: Claude Code writes code → you read every line → ask about anything unclear → only then accept and move on.
Wk 9–10Get comfortable with Claude Code
- Always start inside a Git repo — commit before every Claude Code session
- Use Plan Mode first for anything touching more than 2–3 files
- Set up your CLAUDE.md — the file that tells Claude Code about your project
- Keep CLAUDE.md under 500 lines; add rules only when Claude repeats the same mistake 2–3 times
- Check /context regularly — system tools alone use ~16,800 tokens
📺 Nick's course — Week 9
4-Hour Course: CLAUDE.md + Claude directory (~45 min)
Nick's explanation of CLAUDE.md, the global vs local config, and the Claude directory structure is the best available. Watch this before setting up your first project. His mental model of "project brain" is exactly right.
CLAUDE.mdglobal vs local configproject structure
📺 Nick's course — Week 10
4-Hour Course: Permission modes + Plan Mode (~20 min)
Watch the section on permission modes (ask before edits, edit automatically, plan mode). This directly applies to how you'll use Claude Code safely while you're still learning. Plan mode is your primary tool for anything non-trivial.
plan modepermission modessafety
Phase 3a · Weeks 11–12
Proposal first-draft generator
Feed it a client name, industry, and 3–5 bullet points. It outputs a structured Word-ready proposal draft.
specmulti-file projectstemplatingfile I/O
📺 Nick's course — Week 12
4-Hour Course: Context management (~30 min)
Once you've shipped the proposal generator, watch Nick's context management section. You'll understand it practically now that you've hit context limitations yourself. His explanation of context rot and how to avoid it is directly applicable.
context managementtoken usagesession hygiene
Phase 3b · Weeks 13–14
Meeting notes → action item extractor
Paste raw meeting notes, get back a structured list of owners, actions, and deadlines. Your first direct use of the Anthropic API — calling Claude as a service from Python.
specAnthropic APIenv variablesprompting as programming
📺 Nick's course — Week 14
4-Hour Course: Skills + MCP overview (~30 min)
You've now hit your first genuinely recurring workflow — the API-calling pattern in the meeting notes tool. That's the trigger to create your first skill. Watch Nick's skills section now, then build your first one: a meeting-notes-extraction skill you can invoke any time. The "Skills over MCP" argument from the engineering community (Zhang & Murag, David Gomes) is starting to consolidate — skills are the primary extensibility pattern, not MCP.
skillsrecurring workflowsMCP context
Ph 4
First Deployed Product
Weeks 15–20 · Full assistance mode
Building something with a real user interface, deployed on the internet. Full Claude Code assistance — your job is understanding and modifying, not originating.
Phase 4 Project
MøllerBeck client intake form
A web page where a prospective client fills in their company, situation, and goals. On submit, it emails you a formatted briefing note. Real product, deployed on the internet.
FlaskHTML formSendGridRailway/Renderdeployment
📺 Nick's course — Week 15
4-Hour Course: Complex builds with Plan Mode (~45 min)
Watch Nick build a full-stack proposal generation platform using Plan Mode. This is the closest analogue to your intake form build. Watch it before you start, not after — his planning approach directly maps to how you should structure the build with Claude Code.
plan mode buildsfull-stackdeployment
📺 Nick's course — Week 18 · Reframed
Multi-agent: the contested debate
You won't build multi-agent systems for MøllerBeck — advisory work is low-volume and reasoning-heavy, and a single Claude Code instance handles it. But you need to be able to discuss the pattern with clients evaluating it. Read three pieces from the engineering community pushing back on the naive "more agents = more output" framing: Maggie Appleton's "Two Dozen Agents, Zero Alignment", Sandipan Bhaumik on multi-agent reality vs demos, and Luke Alvoeiro on probability degradation at scale. Then skim Nick's sub-agents section as the practitioner counterweight. The point isn't to build — it's to evaluate when a client says "we're building a multi-agent system."
contested findingsadvisory fluencywhen not to build
📺 Nick's AI Agents course — Week 20
AI Agents Full Course (2 hrs) — watch in full
This is the capstone watch. By Week 20 you have a deployed product and real experience. This course on agent workflows, multi-agent orchestration, and the broader agentic landscape will now read as a map of where to go next — not abstract theory.
agent workflowsorchestrationwhat's next
Hardware — this phase
By Week 15–20 you may feel RAM pressure (8GB). If it's slowing you down, an external SSD for project files (€80–120) buys headroom. The Mac mini decision point arrives after Week 20 — once you have working automations you want running unattended.
↓
Milestones
How to know you're on track
Now60GB+ free on iMac internal drive
Wk 2Can write a loop and a function without help
Wk 4Can read and modify someone else's simple Python script
Wk 6Phase 1 project shipped and used at least once for real work
Wk 8Git repo with meaningful history. Claude Code installed. First 30 min of Nick's course watched.
Wk 10CLAUDE.md set up. Have used Plan Mode at least once.
Wk 12Proposal generator running. Have read every line of the code.
Wk 16Meeting notes tool live. Have called the Anthropic API directly.
Wk 20Client intake form deployed. Shown to at least one real person.
Mo 5+Evaluate Mac mini M5. Begin unattended automation layer.
📖
Parallel Reading Track
1–2 hrs/week throughout
The conceptual layer that makes the technical work meaningful to your clients.
1
Co-Intelligence
Most grounded practitioner take on AI in knowledge work.
2
Anthropic Economic Impact Research
What the people building these tools actually believe about impact.
3
Stanford 120k Developers Study + METR Research
The most empirically grounded data on AI coding productivity. Findings are real but uneven and contested. Read directly, not summaries. This is what calibrates your advisory claims away from vendor marketing — pair it with the Anthropic research above to triangulate.
4
Benedict Evans Newsletter
Technology and business strategy. Sharp, non-hype perspective.
5
The Pragmatic Programmer
Mindset, not tutorial. Read slowly alongside the technical work.
Concepts to discuss fluently by month 4
- What an LLM actually is — probabilistic next-token prediction, not retrieval
- What "context window" means and why it matters for business tools
- The difference between automation (rule-based) and AI augmentation (probabilistic)
- Why hallucination happens and what that means for advisory work