Go from manual operator to AI-enabled practitioner who builds reusable systems, no coding background needed
For procurement, supply-chain, and operations people who want to install Claude Code from scratch, write their first CLAUDE.md, and push a real repo they can show a hiring manager.
3 chapters, 8 lessons
14-day refund on the yearly plan. Real pricing on the plans page, no surprises.
8
lessons, yours to run
Easy to pick up, built to get you the next job
No coding background needed, and you write code with Claude as you go.
Every section below turns into something a hiring manager recognises, not just notes.
Stop solving the same problem twice
- You will reframe every repetitive task as a system worth building once and reusing every time after, not a prompt to retype from scratch
- You will apply the repeatable-beats-clever test to your own work so future versions of the same problem cost you nothing to solve
- You will read real public harness repos and identify exactly what proof-of-process looks like, dated commits, working examples, changelogs, so you can build the same signals into your own portfolio
Install and verify a real AI tooling environment yourself
- You will install Claude Code on your own machine, step by step, with every checkpoint verified before you move on, no prior command-line experience assumed
- You will confirm Node.js, run the npm install, and check the version number so you can say honestly 'I set this up myself from a clean machine'
- You will open your first live Claude Code session and give it a real working task, not a toy demo
Build a GitHub presence that a recruiter actually notices
- You will create a properly configured GitHub profile with a real photo, a one-line bio, and a contact link, the exact setup a hiring manager expects to see
- You will create and name your first repository, add a README, and understand why a private repo for work in progress is a normal professional choice
- You will push your first real commit so the repo has genuine history behind it, not an empty placeholder
Write a CLAUDE.md that makes every future session smarter
- You will write your first CLAUDE.md file, a plain-text context document that means you never have to re-explain your setup to Claude Code again
- You will set up a consistent folder structure (notes, skills, .claude) that every future course in the programme builds on top of
- You will save your first session transcript as harness evidence, the kind of proof-of-process that separates operators who have actually built something from those who only read about it
Finish this course and you can do all of this, no prior background required:
- You will be able to install and configure Claude Code from scratch on your own machine and walk a hiring manager through exactly what each piece does and why.
- You will be able to demonstrate a real GitHub repository with commit history, a professional profile, and a folder structure that shows you work like a practitioner, not a student doing a one-off assi
- You will be able to write a CLAUDE.md that captures your working context so any future AI session, or a new team member, can orient instantly without you repeating yourself.
- You will be able to articulate the difference between a clever one-off prompt and a reusable system, and demonstrate that distinction with a real saved example in your repo.
- You will be able to review a public harness repo and identify the signals of genuine proof-of-process, exactly the analytical habit an employer expects from someone who claims AI tooling experience.
- You will be able to save and organise session transcripts as portfolio evidence, giving you concrete artefacts to point to in an interview rather than vague claims about using AI tools.
8 lessons, 3 chapters
Built by practitioners, not influencers
Every agent, skill file, and dataset is drawn from 25+ years and 50+ Oracle ERP implementations across pharma, manufacturing, semiconductor, and distribution.
Kept current with the stack
Claude Code, skills, and MCP move fast. Your licence includes every system update for as long as you're subscribed. Your system gets better, not obsolete.
You have been told to 'get comfortable with AI tools' without anyone explaining what that actually means in practice. Every time you start a new session you retype the same context, repeat the same formatting instructions, and craft clever one-off prompts that produce one decent result and nothing reusable. Meanwhile job postings for operations and procurement roles are starting to ask for AI tooling experience and your GitHub profile still has the default grey avatar from an assignment you never finished two years ago. The gap between 'I have used ChatGPT' and 'I built and maintain a working AI system I can demonstrate' is exactly the gap that gets CVs filtered out before anyone reads them.
What you'll be able to do, module by module
Every module leaves you able to build and run something real. Here is the syllabus, in the order you work through it.
Curriculum
3 chapters · 8 lessons
Section 1: Thinking in Systems
You will apply the repeatable-beats-clever principle to any recurring task, and you will complete an annotated repo review of real public harness repositories so you can identify what genuine proof-of-process looks like before you build your own.
Chapter 1.1: From Prompting to Building3 items
- L1: Why Repeatable Beats Clever🔒
- L2: Case Study: Inside Two Public Harness Repos🔒
- Quiz: Systems ThinkingQuiz
Section 2: Environment Setup From Zero
You will install Claude Code via npm, verify the install with observable checkpoints, configure a professional GitHub profile, create your first repository with a proper folder structure, and run a real working Claude Code session that produces your first saved harness artefact.
Chapter 2.1: Install and Verify4 items
- L3: Workbook: Install Claude Code🔒
- L4: Workbook: GitHub Account and First Repo🔒
- L5: Workbook: Folder Structure and First Session🔒
- Quiz: Setup VerificationQuiz
Section 3: Your First CLAUDE.md
You will write a CLAUDE.md file that stores your context, preferences, and instructions once so that every future Claude Code session starts already knowing your setup, eliminating the need to re-explain yourself each time.
Chapter 3.1: Write, Test, Iterate4 items
- L6: Workbook: Draft Your Personal Context File🔒
- L7: Workbook: Test It Against 5 Real Tasks🔒
- L8: Case Study: A Context File That Cut Rework by Half🔒
- Course Final: Harness SetupQuiz
Candidates who can open a terminal, install and verify a tool from scratch, maintain a structured repo with genuine commit history, and explain what a CLAUDE.md does and why they wrote one are genuinely rare. Stacking that demonstrated self-sufficiency on top of a procurement or supply-chain background makes you the operator a hiring manager remembers after the interview ends.
From subscribing to running your first artifact
Subscribe and get instant access
Log in, enrol in AC 201, and open the course. Every lesson, workbook step, and checkpoint is waiting for you immediately. No software pre-installed, no prior technical knowledge assumed.
Work through each section with verified checkpoints
Follow the workbook-style lessons in order. Each step tells you exactly what to run, what a successful result looks like, and what to do if it does not match. You confirm Node.js is installed, you install Claude Code, you create your repo, you write your CLAUDE.md. Nothing moves forward until each checkpoint is green.
Run your first real session and save the evidence
By the end of Section 3 you will have Claude Code running, a properly configured GitHub repo with your first commit, a CLAUDE.md that carries your context into every future session, and a saved session transcript that is your first piece of genuine portfolio proof.
From blank machine to first working harness session
Verify Node.js and install Claude Code
You open your terminal, run node --version, and confirm you see v18 or higher. You run npm install -g @anthropic-ai/claude-code, wait for it to finish with no red error text, then run claude --version to confirm the install. You connect your account by following the on-screen prompts. Checkpoint passed: you have a working Claude Code install you set up yourself.
Set up your GitHub profile and first repo
You go to github.com, sign up with a professional username based on your real name, add a real profile photo, and write a one-line bio: 'Operations student building an AI Career OS.' You create a new private repository called ai-career-os, tick the box to add a README, and confirm the repo page shows the README displayed. Checkpoint passed: you have a GitHub presence a recruiter could actually find.
Create your folder structure
Inside your cloned repo folder you run mkdir notes, mkdir skills, mkdir .claude. You now have the standard layout every future course lesson will reference. Checkpoint passed: the three folders exist and you can see them.
Run your first real session and save the transcript
You type claude to start a session, give it a real task (asking it to write a plain-text summary of what this programme covers so far into your notes folder), and read the output. You copy the full session text and save it as notes/session-01.md. This is your first piece of harness evidence: a real artefact with a real timestamp.
Write your first CLAUDE.md and push everything
You write a CLAUDE.md in your repo root that tells Claude Code who you are, what programme you are working through, and what your folder structure means. You commit all new files and push to GitHub. Your repo now has history, context, and evidence. Checkpoint passed: everything is on GitHub and your first harness is real.
The toolkit you'll build and run in this program
You leave with working assets, not notes.
Real things you can demo in an interview.
A fully installed and verified Claude Code environment on your own machine, confirmed with version-number checkpoints
A configured GitHub profile and private repository with your first commit and a proper folder structure ready for every subsequent course
Your first CLAUDE.md file, a plain-text context document that makes every future session start smarter
An annotated repo review worksheet completed against real public harness repositories
A saved first-session transcript stored in your notes folder as your earliest piece of harness evidence
You'll get the most from this if
Procurement, supply-chain, and operations students or early-career professionals who want to add verifiable AI tooling skills to their CV without needing a technical background
Practitioners who have experimented with AI tools but have nothing to show for it, no repo, no system, no evidence, and want to change that
Anyone who has been told to 'get comfortable with AI' and wants a structured, step-by-step path that starts from a completely clean machine
People who are already enrolled in the AI Career OS programme and need to complete the foundational environment setup before building more advanced harnesses in AC 202 onwards
Yearly plan: 14-day keep-the-system guarantee
14-day refund on the yearly plan. Finish the first two modules, and if you haven't run your first live pipeline, take a full refund.
Straight answers before you subscribe
Do I need any coding or technical background to start this course?
None at all. The course is designed as a workbook: every step tells you exactly what to type, what a successful result looks like, and what to do if something does not match. The lessons assume you have never opened a terminal before and build from there. Every checkpoint is designed so you can verify your own progress without needing anyone to interpret it for you.
Will this work on my machine, Windows or Mac?
Yes. The installation lessons cover both Mac (Terminal) and Windows (Command Prompt or PowerShell), and the checkpoints are written so you know what a correct result looks like on either system. The course notes explicitly that exact terminal output varies by machine and version, so you are not expected to match a screenshot perfectly, only to confirm no error and a real version number.
What is your refund policy?
There is a 14-day refund period from the date of enrolment. If you work through the lessons and it is not what you needed, contact the academy within 14 days for a full refund, no complicated process.
How does the course stay current as Claude Code updates?
The course is updated as the tooling changes. The lessons already note that exact output and on-screen wording can vary between versions of Claude Code, so the checkpoints focus on observable results (a version number, no error text, a working session) rather than matching a specific screenshot. When significant updates occur the workbook steps are revised accordingly.
Can I use what I build here in real work or a portfolio?
Yes. The CLAUDE.md, folder structure, session transcripts, and GitHub repo you create in this course are yours. The course is explicitly designed so that what you build becomes portfolio evidence you can show to a recruiter or hiring manager. There are no restrictions on using these artefacts professionally or including them in job applications.