SEO Intel Blog · Use AI properly

How to use AI properly: get consistent, accurate results by setting it up like a filing cabinet, not a chat window

I run several projects with an AI assistant: a website, a charity cricket event, a set of books and a few small tools. For the first few months I did what most people do. I opened a chat, typed what I wanted, and hoped for the best.

Daryn Potgieter21 November 202611 min read

Some days the results were brilliant. Other days the AI forgot what we had agreed the week before, invented a detail, or went off in a direction I never asked for. I would correct it, it would apologise, and twenty minutes later we were somewhere worse.

The fix was not a cleverer prompt. It was treating the AI like a new member of staff who is very fast, very capable and has no memory at all. You would not hand that person a job without a folder, a rulebook and notes from last time. This post shows how I set that up, so you can copy it.

First, how AI actually works (in plain English)

You don't need the technical detail, but three facts change how you use it.

1. It predicts words from what is in front of it. An AI assistant writes its answer by working out the most likely next words, based on everything in the conversation plus what it learned in training. It is very good at this. It is not looking things up in a perfect database unless you give it a tool or a document to look at.

2. It only "knows" what is on its desk. This is why ChatGPT forgets your conversation, loses context or ignores instructions you gave last week, and Claude does the same. Think of each chat as a desk. Whatever is on the desk (your messages, files you share, notes you paste in) is what it works from. When you start a new chat, the desk is cleared. Unless your setup brings your notes back, last week's decisions are gone.

3. Mistakes build on themselves. If one answer is slightly wrong and you carry on from it, the next answer treats that mistake as true. Then the next one does too. This is how a conversation "drifts" and why long, messy chats so often end badly. People call the confident wrong answers "hallucinations".

Why does AI make things up?

AI hallucination means an AI giving an answer that sounds right but is wrong or invented. It isn't lying on purpose. When it doesn't have the facts on its desk, it predicts what a likely answer would look like, and sometimes that prediction is wrong. The more an AI has to fill gaps by guessing, the more it makes things up. The cure is to give it the facts, the documents and permission to say "I don't know".

So the goal is simple: put the right things on the desk every time, and leave as few gaps as possible.

The four things that fixed it for me

  1. Project folders, so every job has a home.
  2. A memory hub, so the AI starts each session knowing where things stand.
  3. A "How we do it" rulebook, so repeat jobs are done the same way every time.
  4. A decision log, so you can see which decisions worked and which didn't.

You can do all of this with ordinary files in a folder. You don't need special software.

1. Project folders: how to organise your AI chats

Make one main folder, and one folder inside it for each project. Mine looks roughly like this:

Projects/
  00 HUB/            <- the map and the rules (more on this below)
  Website/
  Charity Event/
  Books/
  Property/

Inside each project folder, keep:

The point is that when you say "let's work on the website", there is exactly one place to look.

Projects vs chats. ChatGPT and Claude both have a Projects feature. A normal chat starts from nothing. A project keeps its own files and instructions, so every chat inside it starts with that background. Use one project per piece of work, the same way you use one folder per project on your computer, instead of hundreds of loose chats in the sidebar.

2. The memory hub: how to make AI remember things

Built-in memory features help, but they decide for themselves what to keep and they fill up. The most reliable way to make AI remember everything that matters is to keep your own memory files and have it read them at the start of every session. The hub is a small folder that every session reads first. Mine has three files.

START HERE. A one-page map. Each project, its folder, and which file to open first. When I ask for something, the AI matches it to a project from this map instead of guessing.

HOW WE WORK. The general rules for every project. For example:

INBOX. A place for ideas that come up mid-task for a different project, so they are not lost and don't derail what I'm doing.

You don't have to build any of this by hand: one prompt can set the whole thing up with you, and create the files if your AI can reach your computer. The exact prompt we use for this is in the SEO Intel Skills and Prompt Pack.

What goes in a project memory file

Keep it short and current. The top section is the most important:

What not to put in memory

3. "How we do it": write repeat jobs down once

Any job you do more than twice deserves a written method. Mine is a single file with a short section per job. Examples of what goes in it:

The first time I did each of these, it took a long back and forth. Once it was written down, the AI followed the same steps every time, and so did I.

A useful habit: when a job goes wrong and you work out why, add one line to the method so it can't happen the same way again.

4. The decision log: your track record

This is the part most people skip, and it is the most valuable over time.

Every time you make a meaningful decision, write one line:

21 Nov 2026 - Decided to stop offering paid services on the website and
focus on free guides plus low-cost tools. Reason: visitors want help,
not a price. Check results: 27 Nov.

Then, when you check the results, add what happened. Over weeks you build a history of what worked and what didn't, a bit like a weather record. You stop repeating the same mistakes, and when the AI suggests something, you can both look back and see whether something similar worked last time.

I keep two files:

5. Turn your best prompts into fixed instructions

Once a prompt reliably gives you good results, stop retyping it. Save it, and reuse it word for word. Most AI tools now let you store reusable instructions. Some call them skills, some call them projects or custom instructions. The idea is the same: the method is locked in, so you get the same careful process every time instead of a slightly different one depending on how you phrased it that day.

How to turn a job into a skill, and keep it improving, is in What are Claude skills?.

Signs a prompt should become fixed instructions:

Fixed instructions reduce drift and mistakes. They don't make an AI perfect, so keep checking anything that matters.

How a session runs, start to finish

Start:

  1. Say which project. "Website:" or "Books:" is enough.
  2. The AI reads the hub map, then that project's memory file.
  3. Say what you want, and what "done" means: draft, build, publish, or just answer.

During:

End:

Ready-made prompts for starting a session, ending one and the weekly memory tidy are in the SEO Intel Skills and Prompt Pack.

How to write a good prompt for AI (ChatGPT, Claude or Gemini)

Most "best AI prompts" lists are tricks. What actually works is giving the AI the same six things a good manager would give a person. A simple pattern for anything bigger than a quick question:

The six-line request template we use, with an example for each line, is in the SEO Intel Skills and Prompt Pack.

The last line matters more than people think. "Build it but don't publish" has saved me from more mistakes than anything else.

Do you need a paid plan? And does this work in ChatGPT and Gemini?

Short answer: no, you don't need to pay, and yes, it works in all three of the big assistants. The method is just folders, notes and saved instructions, so it isn't tied to one tool.

On a free plan. At the time of writing (November 2026), all three let free users keep work in one place:

What paying adds. Mostly room. Paid plans give you more usage before you hit a limit, more files per project and, in Claude, better handling of large project folders. If you work on the method every day you'll probably notice the limits on a free plan, but you can start without paying and decide later.

Across different assistants. The folders, memory file, decision log and "How we do it" rulebook work anywhere, because they are your own files. Saved instructions are where the tools differ:

Tip for free plans: keep each project's files few and tidy. One short, current memory file beats ten long ones, and it leaves room under the free limits.

Plans and limits change often, so check the current details on each provider's help pages before you rely on them.

Mistakes I made, so you don't have to

Quick start: how to start using AI properly

  1. Make a Projects folder with one folder per project.
  2. Add a 00 HUB folder with START HERE, HOW WE WORK and INBOX.
  3. Give each project a memory file with a NOW section at the top.
  4. Start a "How we do it" file and write down your first repeat job.
  5. Start a decision log today, even if it is one line.
  6. Begin every session with the project name, and end every session by updating memory.

None of this is clever. It is just good filing. But it turns an assistant that forgets everything into one that picks up exactly where you left off, and that is where consistent, accurate results come from.

Sources and further reading

Frequently asked questions

Does AI remember my previous chats?
Only if your setup brings those notes back. Many tools now have memory features, but the most reliable way is to keep your own project notes and have the AI read them at the start of each session.
What is an AI hallucination?
When an AI gives a confident answer that is wrong or made up. It happens most when it has to fill gaps by guessing. Giving it the right documents and clear rules reduces it.
What should I save in an AI memory file?
The current state of the project, decisions made, the rules that must always apply, key facts and what's next. Not passwords, payment details or long transcripts.
Is a skill better than a prompt?
For repeat jobs, yes. A saved set of instructions gives the same method every time, while retyped prompts vary. Neither makes AI perfect, so keep checking anything important.
Do I need a paid AI plan for this?
No. Claude, ChatGPT and Gemini all let free users save projects or reusable instructions (November 2026). Paid plans mainly add more usage and room for files.
Does this work in ChatGPT and Gemini as well as Claude?
Yes. The folders, memory file and decision log work with any assistant. Saved instructions go in a skill or project in Claude, a project in ChatGPT and a Gem in Gemini, and may need small changes to behave the same in each.
Why does ChatGPT forget my conversation?
Each chat only works from what is in it. Long chats get summarised and early details drop out, and a new chat starts empty. Keep your decisions in a project or memory file and have it read that at the start.
How do I make AI remember everything?
You can't make it remember everything, and you don't want to. Keep a short memory file per project with the current state, decisions and rules, and have the AI read it first every time.
What is the difference between projects and chats?
A chat starts from nothing. A project keeps files and instructions that every chat inside it starts with. Use one project per piece of work.
How do I use AI effectively at work?
Give each piece of work its own project, keep a memory file and a written method for repeat jobs, ask in a clear pattern (project, job, why, rules, finish) and check anything that matters before it goes out.

Do it yourself. Skip the mistakes I made.

This guide comes from a real problem on one of my own stores. Here's how to skip it.

1

See what's wrong

Run the free store audit. No account, no card. Built for Shopify; Wix stores get a quick check too.

Run the free audit
2

Fix it yourself with Claude

Skills Pack (Shopify, £14.99): 8 Claude skills that check your store against Merchant Center rules and fix what they find, including suspension recovery.

Skills Pack £14.99
3

Learn how I did it

I cleared my own suspension without paying anyone. The full story, every mistake and every fix, is free to read.

Read how I did it