Tutorialthe whole build, step by step

CLAUDE.md file: leave your AI a four-line note after every fix

A new AI chat can see what you changed, not why. Write four lines after every real fix and keep them where the AI reads first.

By Eric Snyder, founder 6 min readChecked on Oct 4, 2026
Save this guidereceiptsgroup.com/guides/ai-four-line-note
You needThe AI you already use: Claude, ChatGPT or similar
TimeA couple of minutes at the end of a work session
CostNothing extra
Works forAny project you keep coming back to
In this guide
Start here
  1. Start here: paste this into ChatGPT or Claude
The note
  1. Why the AI keeps undoing your fixes
  2. The four lines
  3. Where to keep it so the AI reads it first
  4. What never goes in the note
  5. When to update it
Copy and use
  1. Prompts: let the AI write the note
  2. Copy this: the note checklist
  3. Example (made up)
  4. Mistakes to avoid
  5. Sources, checked Oct 4, 2026

Your AI doesn't remember yesterday, at least not the part that matters. A new chat can see how things look now. It can't see why you made them that way. So it helpfully puts the old way back.

The fix is a short note. After every real fix, write four lines: what changed, why, how we checked it, and what's still open. Keep the note where the AI reads it first. This guide has the template, a filled-in example, where to put it in Claude and ChatGPT, what never goes in it, and prompts that write the note for you.

Checked on Oct 4, 2026

Start herepart 1

Start here: paste this into ChatGPT or Claude

Not technical? Start here. Copy this prompt into ChatGPT or Claude (the free versions work) and it walks you through the whole guide, one step at a time, in plain English. It asks before it assumes anything and checks with you before anything that costs money, reaches a real customer or deletes something. The rest of the page is the same guide, written out, if you'd rather do it yourself.

PromptThe walkthrough prompt (copy all of it)
Hi! Please be my patient guide for this step-by-step guide from Receipts Group: "Leave your AI a four-line note after every real fix"
The guide is here: https://receiptsgroup.com/guides/ai-four-line-note (open it if you can; if you can't, everything you need is below).

About me: I run a small business and I'm not technical. Use plain words and short sentences.

What this guide helps me do: A new AI chat can see what you changed, not why. Write four lines after every real fix and keep them where the AI reads first.

How to help me:
1. One step at a time. For each step, tell me in a sentence what it's for and exactly what to do (where to click, what to type, who to ask). Then stop and wait until I say "done" or tell you what I see.
2. Ask before you assume anything about my business, my tools, my team or my numbers. One question at a time.
3. If you use a technical word, explain it in plain English the first time.
4. Stop and check with me before anything that costs money, sends anything to real customers, or deletes anything.
5. Use only what I tell you or show you. Never make up numbers, names, results or quotes. If something's missing, ask me.
6. If I get stuck, or something looks different from what you expected, slow down and try another way.

The steps, from the guide:
Step 1. The four lines.
After every real fix, write these four lines. A real fix is one you'd hate to see undone. One or two sentences each, plain words, date on top.
- What changed: The change, in plain words, and where it lives. So the AI knows the new way is on purpose.
- Why: The problem it fixed, or the decision behind it. The one line the AI can't figure out on its own.
- How we checked it: The test you ran and what happened. Or "Not checked yet.": So nobody trusts a fix that was never tested.
- What's still open: What's left to do, or a question nobody has answered. So the next chat starts where you stopped.
Step 2. Where to keep it so the AI reads it first.
Put the note where the AI reads it at the start of every chat, not buried in an old chat. Newest note on top.
- Claude (the app): A project's instructions: Click Projects (or go to claude.ai/projects), then + New Project. In the project, click Set project instructions, paste the note, and click Save instructions. Claude uses them in every chat in that project. Free accounts get projects too, up to five.
- ChatGPT: A project's instructions: Select New project in the sidebar. In the project, open the more options menu (•••), select Project settings, and add the note to the instructions. They apply only inside that project.
- Claude Code: The CLAUDE.md file in your project folder: A plain text file. Claude Code reads it at the start of every session.
- OpenAI Codex: The AGENTS.md file in your project folder: Codex reads AGENTS.md files before doing any work.
- Anything else: The first message of a new chat: Keep the note in a doc. Paste it in first, before you ask for anything.
Keep the newest notes in the instructions. Move older ones to a notes file in the same project: in Claude, add it to the project's knowledge with the + button; in ChatGPT, add it as a project file. ChatGPT can also save a reply to the project with Save to project (OpenAI says the label may vary).
Step 3. What never goes in the note.
- Passwords, API keys and login codes. (An API key is a password one app uses to talk to another.) Write where it's kept, like "the key is in the password manager," never the key itself.
- Customer details. No names, phone numbers, addresses, or anything about one customer's job. Write "a customer," or use a test name.
- Payment details. No card or bank numbers, ever.
- Whole chat transcripts. Paste the decision, not the conversation. The four lines are the point.
If you share a project, the people you share it with can see its instructions. Write the note like a coworker will read it. They might.
Step 4. When to update it.
- After every real fix. Not every tiny edit. Just the ones you'd hate to see undone.
- When the plan changes. Fix or delete the old note that same day. Otherwise tomorrow's AI gets very confident instructions from a version of the project you already gave up on.
- When something "still open" gets done. Write a new note. Its "What changed" line closes the old question.
- When the notes get long. Keep the newest up top and move the rest to a notes file. Short wins: Claude Code's docs say the more specific and concise your instructions, the more consistently Claude follows them.

When we get to it, use "The four-line note" from the guide (fill in the blanks and brackets with my details):
---
HANDOFF NOTE · [date]
What changed:
Why:
How we checked it:
What's still open:
---

When we get to it, use "Before you save the note" from the guide (fill in the blanks and brackets with my details):
---
BEFORE YOU SAVE THE NOTE
[ ] Date on top
[ ] What changed, in plain words
[ ] Why: the real reason
[ ] How we checked it
    (or "Not checked yet")
[ ] What's still open
[ ] No passwords, keys or codes
[ ] No customer details
[ ] Saved where the AI reads
    it first
[ ] Old notes it replaces are
    deleted or updated
---

Watch out for these (the guide's mistakes to avoid):
- Skipping the "why." The change is easy to see. The reason isn't. That's the line that stops the undo.
- Pasting the whole chat. The AI has to dig for the decision. Four lines beat a wall of chat.
- Leaving old notes up. A note for a plan you dropped is worse than no note. Delete it or mark it replaced.
- Saying it's tested when it isn't. "Not checked yet" is a fine answer. A guess isn't.
- Putting a password in "just for now." Write where it's kept instead.
- Treating the note like a lock. It's information, not a rule the AI can't break. Claude Code's docs say it treats these files "as context, not enforced configuration." Still check what the AI changes.

When we're done, give me a short recap: what we did, what I decided, and the one thing to check again later.

Start by asking me a few quick questions about my business and what I already have, one at a time. Then begin with step 1.
The noteparts 2 to 6

Why the AI keeps undoing your fixes

Every new chat is the AI's first day on the job. Because it is. Claude Code's docs put it plainly: "Each Claude Code session begins with a fresh context window." (A session is one stretch of work. The context window is everything the AI can see while it works.) And Claude's help page on projects says context isn't shared across chats in a project unless you add it to the project's knowledge.

So say you changed how bookings get confirmed. Tomorrow's chat sees the new setup, not the reason. It looks a little odd, so the AI "fixes" it and puts the old way back. You explained the reason once, in some chat, somewhere. Good luck finding it.

Honestly, this one's mostly for me. I bounce between projects all day. The note is how I stop explaining the whole business again.

The note doesn't retrain the AI or change it for good. It's information the AI reads at the start, like a sticky note on the monitor for whoever sits down next.

The four lines

After every real fix, write these four lines. A real fix is one you'd hate to see undone. One or two sentences each, plain words, date on top.

LineWhat to writeWhy it's there
What changedThe change, in plain words, and where it lives.So the AI knows the new way is on purpose.
WhyThe problem it fixed, or the decision behind it.The one line the AI can't figure out on its own.
How we checked itThe test you ran and what happened. Or "Not checked yet."So nobody trusts a fix that was never tested.
What's still openWhat's left to do, or a question nobody has answered.So the next chat starts where you stopped.
The four-line note
HANDOFF NOTE · [date]
What changed:
Why:
How we checked it:
What's still open:

Where to keep it so the AI reads it first

Put the note where the AI reads it at the start of every chat, not buried in an old chat. Newest note on top.

If you usePut the note inHow
Claude (the app)A project's instructionsClick Projects (or go to claude.ai/projects), then + New Project. In the project, click Set project instructions, paste the note, and click Save instructions. Claude uses them in every chat in that project. Free accounts get projects too, up to five.
ChatGPTA project's instructionsSelect New project in the sidebar. In the project, open the more options menu (•••), select Project settings, and add the note to the instructions. They apply only inside that project.
Claude CodeThe CLAUDE.md file in your project folderA plain text file. Claude Code reads it at the start of every session.
OpenAI CodexThe AGENTS.md file in your project folderCodex reads AGENTS.md files before doing any work.
Anything elseThe first message of a new chatKeep the note in a doc. Paste it in first, before you ask for anything.

What never goes in the note

  • Passwords, API keys and login codes. (An API key is a password one app uses to talk to another.) Write where it's kept, like "the key is in the password manager," never the key itself.
  • Customer details. No names, phone numbers, addresses, or anything about one customer's job. Write "a customer," or use a test name.
  • Payment details. No card or bank numbers, ever.
  • Whole chat transcripts. Paste the decision, not the conversation. The four lines are the point.

If you share a project, the people you share it with can see its instructions. Write the note like a coworker will read it. They might.

When to update it

  • After every real fix. Not every tiny edit. Just the ones you'd hate to see undone.
  • When the plan changes. Fix or delete the old note that same day. Otherwise tomorrow's AI gets very confident instructions from a version of the project you already gave up on.
  • When something "still open" gets done. Write a new note. Its "What changed" line closes the old question.
  • When the notes get long. Keep the newest up top and move the rest to a notes file. Short wins: Claude Code's docs say the more specific and concise your instructions, the more consistently Claude follows them.
Copy and useparts 7 to 10

Prompts: let the AI write the note

You don't have to write the note from memory. At the end of a session, ask the AI to draft it, then check it yourself. At the start of the next one, tell the AI to read it first. These work in Claude, ChatGPT, or any AI assistant.

Prompt1 · End of a session: write the note
Before we stop, write a handoff note for this session, so the next chat can pick up without me explaining everything again.

Use exactly these four lines, one or two plain sentences each, with today's date on top:
What changed:
Why:
How we checked it:
What's still open:

Rules:
- Only include what we actually did and decided in this chat. If we didn't test something, write "Not checked yet." Don't guess.
- "Why" matters most. Give the real reason for the change, in my words if I said it.
- No passwords, API keys, login codes, or customer names, numbers or addresses. If one matters, say where it's kept instead.
- If we made more than one real fix, write one note per fix.
Prompt2 · Start of a session: read it first
Before you change anything, read the handoff notes in this project's instructions (or in CLAUDE.md or AGENTS.md if we're working in a code folder). Then tell me in three short bullets: what we changed most recently, why, and what's still open. If anything I ask for today would undo one of those changes, stop and ask me first.
Prompt3 · Once in a while: clean up old notes
Here are my handoff notes. Find any that conflict with each other or look out of date, list them, and tell me why. Don't delete or rewrite anything until I say so. Then suggest a shorter version that keeps every decision that's still true, newest first.

[paste your notes]

Read the draft before you save it. If the "Why" line is vague, fix it. That's the line you'll need most.

Copy this: the note checklist

Before you save the note
BEFORE YOU SAVE THE NOTE
[ ] Date on top
[ ] What changed, in plain words
[ ] Why: the real reason
[ ] How we checked it
    (or "Not checked yet")
[ ] What's still open
[ ] No passwords, keys or codes
[ ] No customer details
[ ] Saved where the AI reads
    it first
[ ] Old notes it replaces are
    deleted or updated

Example (made up)

Everything here is made up: a demo project and a test customer.

Northside Heating & Air uses an AI assistant to help run its booking messages. Customers used to get a booking confirmation by text and by email. Some thought they'd booked twice and called to cancel. So the team switched to text only, and wrote this note:

A filled-in note (DEMO)
HANDOFF NOTE · 2026-10-02 (DEMO)
What changed: Booking
  confirmations go by text only.
  The email copy is turned off.
Why: Customers got a text AND an
  email and thought they'd booked
  twice. Some called to cancel
  the "extra" visit.
How we checked it: Booked a test
  visit for "TEST Jordan Sample"
  on the office test phone. One
  text came. No email.
What's still open: Reschedule
  messages still send an email.
  Switch those too? Decide Friday.

The next day, someone asks the AI to "make sure every customer gets a confirmation email." With the note in the project's instructions, the AI can see the email was turned off on purpose, and why. With prompt 2 above, it's told to stop and ask before undoing it. Without the note, all it sees is a missing email.

Mistakes to avoid

  • Skipping the "why." The change is easy to see. The reason isn't. That's the line that stops the undo.
  • Pasting the whole chat. The AI has to dig for the decision. Four lines beat a wall of chat.
  • Leaving old notes up. A note for a plan you dropped is worse than no note. Delete it or mark it replaced.
  • Saying it's tested when it isn't. "Not checked yet" is a fine answer. A guess isn't.
  • Putting a password in "just for now." Write where it's kept instead.
  • Treating the note like a lock. It's information, not a rule the AI can't break. Claude Code's docs say it treats these files "as context, not enforced configuration." Still check what the AI changes.

Stop explaining it twice

Four lines after every real fix: what changed, why, how we checked it, what's still open. Keep them where the AI reads first, keep them current, and keep secrets out. I already explain enough things twice. I'm not paying a computer to forget the same thing I forgot.

Checked on Oct 4, 2026 against

Every claim about a third-party tool in this guide (plans, prices, menu paths, commands, limits) was checked against these official pages on Oct 4, 2026. These screens change often: if something looks different, trust the page over this guide.

Rather skip the setup?

Want help setting this up?

Receipts Group builds these systems. Thirty minutes with Eric tells you which piece is worth building first, or that none of them are. The guides stay free either way.

Keep going

more free guides