Next workshop If you need the tech to explain it, you don't have a product RSVP now

Ways to set AI up to help

Before AI can help well, you set it up. Left cold it guesses at your conventions every time; given the right context once, it builds the way your project already does. This page is about that groundwork: the memory, rules and context you put in place so the AI starts each task already knowing how your work is meant to go.

Memory and rulesProject contextConventionsAIBuilds the way yourproject already does
Set up once and the AI starts each task already knowing how your work is meant to go. The memory, rules and context you put in place are what stop it guessing your conventions every time.

Project memory and rules

The first piece of setting AI up is giving it your project's memory and rules, the conventions, context and standards it should already know before it starts. Claude reads these from CLAUDE.md files and rules, so getting their structure right is how it builds the way your project already does.

Say it another way

Project memory is a plain file, called CLAUDE.md, where you write your project's conventions and decisions. The AI reads it before every task, so it starts already knowing the house rules, like handing a new hire the team handbook on day one rather than letting them guess.

User~/.claude, personal, every projectProject.claude/ or root, shared in the repoDirectorya subfolder, a specific partbroadspecific
The CLAUDE.md layers you will usually use, broad to specific: personal at the user level, shared at the project level, granular in a subfolder. Each layer adds detail for a narrower scope, and you keep each one modular with @import or a .claude/rules/ folder rather than one giant file.

Doing this with Claude Code: Project memory and rules

Give Claude its instructions through CLAUDE.md files and rules, laid out so the right guidance is already in place before it starts a task, and so each session is consistent.

It earns its keep in four ways: layer by scope, keep it modular, scope rules to where they apply, and check what actually loaded.

Layer it by scope. User-level for your personal preferences across every project, project-level for the shared conventions that travel in the repo, directory-level for a specific part. Each layer down is narrower and adds detail.

Keep it modular, not one giant file. Split it into focused topic files, either pulled in with @import or kept as a .claude/rules/ folder, so each concern lives in its own file.

Scope a rule to where it applies. Give a rule a path so it only loads when Claude is working on matching files, so its context is not filled with rules that are not relevant.

Check what actually loaded. /memory shows which files are in play this session, so when behaviour is off you can tell a wrong instruction from one that simply never loaded.

Still to come

Three things are still to come, each its own section. First, custom slash commands and skills, your own saved shortcuts and ready-made abilities you set up once and call by name, like a one-word command for a job you do often. Then path-scoped rules, guidance that switches on only for the part of the project it applies to, so the right instructions appear at the right moment and nowhere else. And the tools and information Claude can reach, like MCP servers, a standard way to connect Claude to your files and other apps, so it is not working blind.

Say it another way

Those three terms, in plain words:

  • Custom slash commands and skills are like saved shortcuts. You set a job up once, then call it by a short name instead of explaining it from scratch every time, the way a recipe saves you working the dish out again.
  • Path-scoped rules are like sticky notes that only appear on the drawer you have open. The AI gets the right reminder exactly when it is working on that part, not all of them at once.
  • MCP servers are like the sockets on a wall. They are a standard way to plug the AI into your other things, your files or another app, so it can actually use them instead of working blind.

This page is lighter than the others for now, with more sections still to come.

In plain words

In plain words: this page is about setting AI up before you ask it to build, so it already knows how your project works. You give it your project's memory and rules, the conventions and standards it should follow, written in a file it reads each time it starts. Set up once, it builds the way your project already does instead of guessing every time. AI here means a coding tool like Claude.

Part of Working with AI. The soft skills behind it: The soft skills of working with AI.

Why Claude. When this page carries tool-specific notes they use Claude Code, because it is one of the most widely used AI tools for building software. It is also what we build with day to day. The moves themselves are general and carry across to other capable AI tools.