JDCS
Get in touch
Start a conversation Or call 0418 858 937

jdcs.au · Mid North Coast, NSW

Free course · for builders · 5 lessons · about 36 min

Put Claude Code to work.

Put Anthropic's coding agent to work without the hype. Claude Code lives in your terminal and works step by step behind a permission dial you control, with plan mode, subagents and MCP connections to your own tools. Five short lessons on what it actually is, how to set it up safely on a real repo, the jobs it handles well, and how to keep people in the loop. For technical founders and small dev teams who can read a diff, from a consultancy that builds with it daily.

Start lesson 1 Get the workbook

For technical founders and small dev teams who want a coding agent earning its keep without the cowboy stuff. Honest workflow, real safety habits, and the judgement that keeps it an asset. Taught by a consultancy that builds with it daily.

What you'll learn
Lesson 1 What Claude Code is, and where it fits Claude Code is Anthropic's coding agent: you give it a task in plain language in your terminal, and it reads your codebase, edits across files, and runs the tests. A clear picture of what it is, the forms it comes in, and where it fits a small team. 7 min
Lesson 2 Setting it up safely Permission settings, what it can read, run and edit, and the approvals that keep you in control. Start small in a branch or sandbox, review every change, and lean on CI as the backstop. 8 min
Lesson 3 The real jobs it's good at Features inside a design, refactors, tests, debugging, codebase questions and multi-file changes: the well-shaped work the agent handles well, with subagents for the bigger jobs. And the calls to keep firmly with people. 8 min
Lesson 4 Keeping humans in the loop Review every diff, connect tools through MCP carefully, keep secrets well clear, and let hooks and CI run as automatic guardrails. The habits that keep the agent an asset rather than a liability. 7 min
Lesson 5 Put it to work Pick a few well-scoped jobs, set your permissions, and run the scope, run, review and merge loop with approvals on as it goes. Turning all of it into a calm plan you start on Monday. 6 min

Work through them in order. The single way in is lesson 1.

Carry on anywhere.

Start on your laptop, finish on the train. Save your spot and we'll email you a link that picks the course back up on any device. No account, no password.

Pick up anywhere

Save your progress

Pop your email in and we'll send you a link to pick up where you left off, on any device. No account needed.

Just for the link to your progress. No spam, and I never share your details.

Take it to your team.

A short working session you do together: find where a coding agent helps, scope your first two or three tasks, agree the permissions and guardrails, and write your review and secrets policy. Type into it or print it. Want just the gist? There's a free one-page summary too.

Free download

Get the Claude Code rollout workbook

Pop your email in and the fill-in workbook is yours: spot where a coding agent helps, scope your first tasks, set the permissions and guardrails, and write your review and secrets policy. Type into it or print it.

Your email gets you the workbook, that's it. No spam, and I never share your details.

Prefer the quick version? Read the free one-page summary →

Before you start.

Is the course really free?
Yes, completely. All five lessons are free to read with no sign-up. If you'd like the fill-in rollout workbook to scope your first tasks and set the guardrails with your team, that's a quick email, and that's the only thing asked for anywhere on here. There's a free one-page summary too, with nothing asked for.
Who is this for?
Builders: technical founders, small dev teams, and ops people who can read a diff or manage coders. We assume you're comfortable with a repo, branches and a pull request. If that's not you yet, the AI & automation course is a gentler starting point.
Will it teach me to write code?
No. It's about working well with an agent that writes code: scoping tasks, setting it up safely, knowing the jobs it does well, and keeping a human reviewing every change. The point is judgement and workflow, not syntax.
How long does it take?
About 36 minutes all up, across five short lessons. Read it in one sitting or one lesson at a time, whatever suits.
Will it go out of date as the tools change?
The products move fast, so the course sticks to what lasts: the workflow, the safety habits, and the kinds of work an agent does well. We keep clear of exact menus and plan names that change month to month.
Is this just a sales pitch?
No. It's the same honest advice JDCS would give in a conversation, written down, so you walk away genuinely more capable. We build with Claude Code ourselves, so it's grounded in real use. If you later want a hand putting an agent to work in your team, the first conversation is free and you keep the plan either way.
When you're ready

Want an agent set up properly in your team?

Once you've trialled a few tasks, the next step is fitting an agent into how your team actually ships: the right permissions, a sensible review flow, and secrets kept well clear. That first conversation is free, and you keep the plain-English plan either way.

Start a conversation