A Practitioner's Guide · collinwilkins.com

Getting Started
with AI Tools

The 15-minute setup that turns ChatGPT or Claude from a clever search box into something that knows you, your work, and how you like things done.

By Collin Wilkins  ·  A do-it-with-me guide  ·  Free to share
A Practitioner's Guide · collinwilkins.com

Stop starting from zero every time you open an AI tool.

You're already using ChatGPT or Claude. This is the setup that turns it from a clever search box into something that actually knows you, your work, and how you like things done. No code required.

By Collin Wilkins  ·  A do-it-with-me guide. Read it once, set it up as you go, keep the files forever.

Start here: paste this into Claude or ChatGPT

It interviews you for about five minutes, then writes your reusable AI setup files. This is the whole guide compressed into one prompt. Everything below explains what it's doing and where the files go.

You're going to help me set up a reusable context profile for working with AI tools. I want files I can reuse in every session so I don't re-explain myself every time.

Interview me one question at a time. Do not ask everything at once. Cover:

1. My work — my role, what I'm responsible for, what I'm trying to get done over the next few months.
2. My tools — what I work in day to day (apps, file types, whatever's relevant to me).
3. How I like to work with AI — plan first or just do it, how blunt you should be, response length, anything that annoys me.
4. My recurring tasks — the things I'd hand to an AI every week if it already knew my context.
5. If I create content — who it's for, my tone, one or two things I'd say and one or two I never would. Skip this if it doesn't apply to me.

Ask a follow-up when an answer is vague. When you have enough, output three files as separate Markdown code blocks:
- about-me.md — who I am and what I'm working on
- working-preferences.md — how I want you to collaborate with me
- brand-voice.md — only if I create content

Keep each file under ~200 words, in my words, no generic filler. Ask me the first question now.
What you'll have in 10 minutes: three small text files. The rest of this guide shows you exactly where each one goes, depending on which tool you use.
The Landscape in 60 Seconds

Every AI tool you've heard of is one of three things

Most people only ever use the first one. That's like buying a Swiss Army knife and only using the toothpick. Here's the whole knife, and you don't need to be technical to use any of it.

💬 The front door

Chat & Browser

You type, it answers. Great for drafting, summarizing, and questions. It forgets everything between sessions, and that wall is where most people quietly give up on AI.

Claude.ai · ChatGPT · Gemini
⌨️ The power interface

Terminal & IDE

It reads your files, runs commands, and does multi-step work in your real environment. Same conversational feel, except now it can actually touch your stuff.

Claude Code · Cursor · Cline
☁️ Fire & forget

Cloud Agents

Describe a task, walk away, come back to a finished result. Works best on clear jobs you could hand to a competent junior with a short brief.

OpenAI Codex · Claude Code (background)
More hands-onMore autonomous
Do It With Me · Part 1

Build your AI context profile

This is the part that separates casual users from people who get real work done. The same model gives two people wildly different results, and the difference is almost always this: one of them set up context once, the other re-explains themselves every session.

1

Run the interview prompt

Open Claude or ChatGPT, paste the prompt from the top of this guide, and answer its questions like you're briefing a sharp new contractor on day one.

What good output looks like
about-me.md — a real example
# About Me

I run marketing and ops for a 12-person SaaS company. I'm not
an engineer. I live in Notion, Gmail, Google Sheets, and our
analytics dashboard. I write in plain English and I'm comfortable
following step-by-step instructions, including the occasional
terminal command if you walk me through it.

## What I'm working on
- Q3 launch: landing page copy, email sequence, launch checklist
- Monthly metrics report I rebuild by hand every time (hate this)
- Keeping our help docs current as the product changes

## What I'm not
A developer. Skip the jargon. If a task needs a tool I don't
have open, tell me what to install and why before we start.
2

Put the files where the AI will actually read them

Same files, different homes depending on your tool. Find the row that matches how you work and follow it.

Where each file goes
Claude.ai     →  Create a Project, paste files into Project knowledge
ChatGPT       →  Settings → Personalization → Custom Instructions
Claude Code   →  Save in your working folder as CLAUDE.md
Cursor        →  Save as .cursorrules in your project root
What good output looks like
working-preferences.md — a real example
# How I Like To Work

- Show me a short plan before anything multi-step. I'll say go.
- Be blunt. If my idea is weak, say so and tell me why.
- Keep answers tight unless I ask you to go deep.
- Don't produce final copy. Give me two or three options.
- When you're unsure, ask one sharp question instead of guessing.
💡
Quick win: if you skipped the interview, just write three bullet points for each file by hand. A rough version beats no version. The AI fills the gaps from there.
Do It With Me · Part 2

Get more out of the tool you already use

You don't need a new tool. You need the one you have to stop forgetting who you are. This is five minutes and it changes every conversation after it.

1

Load your profile into ChatGPT or Claude

ChatGPT calls it Custom Instructions. Claude calls it Projects. Same idea: context that survives between chats so you stop repeating yourself.

Paste this if you skipped the interview
Here's context about me. Use it in every reply unless I say otherwise.

WHO I AM: [your role, what you're responsible for]
MY TOOLS: [the apps and files you work in]
HOW TO HELP ME: be direct, plan before multi-step work, keep
answers tight, give me options instead of one final version,
ask a sharp question when you're unsure instead of guessing.

Acknowledge in one line, then wait for my first real task.
What good output looks like
ChatGPT Custom Instructions — filled in
What should ChatGPT know about you?
Marketing/ops lead at a small SaaS company. Not technical.
Work in Notion, Gmail, Sheets. Currently running a Q3 launch.

How should ChatGPT respond?
Be direct and brief. Plan before multi-step tasks. Give 2-3
options, not one polished answer. Plain English, no jargon.
Ask one question if unsure instead of guessing.
2

Run three real tasks this week

Not "write me a poem." Real work builds intuition that toy prompts never will. Pick three things you actually have to do.

Try these
1. Paste a long doc you need to read → "Summarize this for
   someone in my role. What needs a decision from me?"

2. The email you've been avoiding → "Draft a reply. Match
   the tone of my last message in this thread."

3. Something you're learning → "Explain this like I have 15
   minutes and a real reason to care, not a textbook."
💡
The shift to watch for: the first time it answers as if it already knew you, you'll stop treating it like a search box. That moment is the whole point of the setup.
The Configuration Layer

Soul files: the same idea, four names

Once you move past chat, every serious tool reads a plain text file at the start of each session to learn your project. The names differ. The idea is identical: a file the AI reads so it doesn't guess.

ToolFile nameWhere it lives
Claude CodeCLAUDE.mdRoot of your project
OpenAI CodexAGENTS.mdRoot of your project
Cursor.cursorrulesRoot of your project
GitHub Copilot.github/copilot-instructions.mdThe .github/ folder
Emerging standardAGENTS.mdRoot of your project

The minimum version that already works

Ten lines. This alone stops the most common failure: the AI producing something that technically works but ignores how you do things.

CLAUDE.md / AGENTS.md — minimum viable
## Project Overview
This is a Next.js store for selling custom furniture.
Stack: TypeScript, Tailwind, Supabase.

## Conventions
- Named exports, not default exports
- Tests live next to the file they test
- Run tests with: npm test
📦
Want the templates? They're part of the AI Adoption Playbook. The CLAUDE.md and AGENTS.md starters, the AI Readiness Worksheet, and this guide are free to use. No email required.
Do It With Me · Part 3

Try a terminal agent once

The terminal sounds intimidating. The interaction is the same as chat: you type plain English, it responds. The difference is it can read and change real files on your computer. You only have to do this once to get it.

1

Install Claude Code

One command. If you don't have Node or Homebrew, ask ChatGPT "how do I install Homebrew on a Mac" first and follow it.

npm install -g @anthropic-ai/claude-code

# or, if you use Homebrew:
brew install claude-code
2

Point it at a folder and give it a real job

Make a folder of files you actually have (notes, a messy spreadsheet export, a pile of docs). Open it, run claude, and try this.

A good first task
Look at every file in this folder. Tell me what's here in
plain English, flag anything that looks duplicated or out of
date, and propose a cleaner folder structure. Show me the plan
before you move or rename anything.
💡
Why this one: it's safe (it shows a plan before touching anything), it's real, and it does something a chat window physically can't, which is the moment terminal agents click.
Do It With Me · Part 4

Hand a task to a cloud agent

Cloud agents work while you do something else. The skill isn't technical. It's learning to scope a task tightly enough that a competent stranger could do it from your description alone.

1

Learn the difference between a good and bad ask

This single distinction is most of the value. Vague task in, mediocre result out. Every time.

Scope it like this
✗ Bad:  "Build me an app."
✗ Bad:  "Improve the signup flow."

✓ Good: "Add email-format validation to the signup
        form. Show an inline error. Write a test for it."
✓ Good: "Add a dark-mode toggle to the settings
        page. Persist the choice. Match existing styles."
2

Use this hand-off template

Paste it into Codex or push it as a background task in Claude Code. Then close the tab and come back later.

TASK: [one specific, self-contained change]
DONE WHEN: [how I'll know it worked — the visible result]
CONSTRAINTS: [match existing patterns, don't touch X, etc.]
IF UNSURE: stop and leave a note rather than guessing.

Show the change as a pull request I can review.
💡
Mental model shift: stop thinking "AI as copilot." Start thinking "AI as an async teammate you brief and review." That reframe is the whole skill.
Make It Stick

The memory problem, and the free fix

Every tool here forgets between sessions unless you give it somewhere to remember. The fix is not a product. It's a folder of plain text files the AI can read and write directly.

📄 Start here

Plain files

A folder of markdown notes: decisions, preferences, project context. Point your AI at it. Not sophisticated. Works today, costs nothing.

Any text editor
🗂️ Be careful

Notion / OneNote

Fine for you, awkward for AI. The content sits in a format agents can't read directly, so you're back to copy-pasting. Friction returns.

Export step required
🧠 The recommendation

Obsidian

Everything is plain markdown in a local folder. No proprietary format, no export step. The agent reads and writes it natively. This is what I use.

Free · plain text
🔑
The one principle: AI tools work on text. Keep your knowledge in plain text the AI can read natively, and the integration is free and automatic. Everything else is preference.
Pick Your Path

Where to start, based on where you are

You don't have to do all of this. Pick the column that sounds like you and do those three things this week.

🌱

New to AI

Barely used it
  1. Open Claude.ai or ChatGPT, both free, pick either
  2. Run the interview prompt at the top of this guide
  3. Do three real tasks this week, not toy prompts
Go deeper: What is a harness? →
🔧

Technical, unconfigured

Code, but no setup
  1. Install Claude Code, run it in a real project
  2. Add a CLAUDE.md or AGENTS.md from the templates
  3. Create about-me.md and working-preferences.md
Go deeper: Context engineering →
🚀

Daily user

Already in deep
  1. Audit your config layer, is it current and honest?
  2. Set up a real memory system in Obsidian
  3. Delegate a scoped job to a cloud agent
Go deeper: My daily workflow →