# ChatGPT Custom Instructions, Memory and Projects for Marketers

> How marketers should split brand voice and context across ChatGPT custom instructions, memory and projects, with templates to paste.

Source: https://mentionx.ai/learn/chatgpt/chatgpt-custom-instructions-memory-projects  
Author: Dipuck Jones, founder of MentionX  
Updated: 4 November 2026  
Level: Practitioner

**Put rules that apply everywhere in custom instructions, put brand and campaign context in a project, and treat memory as a convenience you review, not a place to store your brand guide.** Projects are the workhorse for marketers: one per brand, client or major campaign, each with its own instructions and files.

> **Key takeaways**
>
> - Custom instructions apply to all chats. Free and Go allow 1,500 characters; paid and workspace plans allow 5,000.
> - Project instructions override custom instructions inside the project.
> - Project-only memory keeps a client's context sealed off. Shared projects always use it.
> - ChatGPT Work can't run inside a project set to project-only memory, so plan which projects need Work.
> - Memory can show its sources under a response. Check them when an answer seems oddly personal or out of date.

*Checked 4 November 2026 (CET) against OpenAI help center articles and chatgpt.com pages. ChatGPT changes often, so confirm plan details in your own account. "Our view" marks MentionX opinion. Ledgerline is a fictional company used for illustration.*

## What goes where?

| Layer | Scope | Best used for | Avoid |
|---|---|---|---|
| Custom instructions | Every chat | Your role, writing preferences, house style rules | Client details, campaign facts |
| Project instructions | One project | Brand voice, audience, product facts, banned claims | Anything secret you'd not want collaborators to see |
| Project files | One project | Brand guide, fact sheet, personas, approved proof points | Out-of-date decks |
| Memory | Varies by setting | Small recurring preferences ChatGPT learns | Anything you need to be exact |

OpenAI's memory article says memory can draw on past chats, saved memories, custom instructions, files in Library or Space and connected apps such as Gmail, depending on plan and region. It also says memory does not keep every detail. That is why exact facts belong in project files.

## What should your custom instructions say?

Keep them about you, not about a brand. Here's a template that fits the 1,500-character limit.

```
I'm a [role] at a [B2B/B2C] company selling [category] to
[audience]. When I ask for copy: be direct, use British/US
English, short sentences, no hype words (revolutionary,
seamless, unlock). When you state a fact that isn't from my
files, say where it comes from or mark it [CHECK]. When a
task is ambiguous, ask one question before answering. Default
to tables for comparisons.
```

## How should you set up a brand project?

Create one project per brand or client. In Project settings, add instructions and set the memory option. Then upload a short set of files.

```
PROJECT INSTRUCTIONS: [Brand]
Audience: [who, their job, what they're measured on].
Voice: [three rules plus one example sentence].
Product facts: use only the attached fact sheet.
Proof points we may cite: [list]. Nothing else.
Never claim: [list, e.g. "guaranteed savings", named customers
without approval].
Competitors: refer to them as Competitor A-D in drafts.
Output defaults: headings in sentence case, UK spelling.
```

Good files to attach: a one-page fact sheet, a voice guide with three published examples, two or three personas built from real interviews, and an approved claims list. Keep each short. Long brand books dilute what matters.

## When should you use project-only memory?

Use it for client work, regulated products and anything you'd not want leaking into other chats. OpenAI's projects article lists what changes: saved memories are not used in the project, chats can reference only chats in the same project, and outside chats can't reference it. Shared projects are always project-only.

One trade-off: ChatGPT Work isn't available in a project-only memory project. If a project needs Work (lesson 11), use default memory and keep sensitive material out.

## When does memory help, and when does it hurt?

Memory helps with small preferences: your time zone, how you like tables, the brands you work on. It hurts when it carries an old fact into a new context, such as last year's pricing. When an answer seems to know something it shouldn't, look for the Sources line under the response; OpenAI says it can show the past chat, saved memory or file that shaped the answer. For one-off sensitive work, a temporary chat stays out of history and isn't used for training while it remains temporary, though it can still use existing memories and instructions unless you switch personalisation off.

*Our view:* most marketers put too much in memory and too little in project files. If a fact has to be exact, it belongs in a file you can update.

> **Pro move:** add a "facts last checked" date at the top of your fact sheet and ask ChatGPT to warn you if the date is more than 60 days old. Stale facts are the most common cause of wrong copy from a well-set-up project.

## Worked example: Ledgerline's projects

*Ledgerline is a fictional accounts-payable tool. Details are illustrative.*

Ledgerline set up three projects: "Brand content" (default memory, used with Work for decks and docs), "Customer research" (project-only, holding interview notes) and "Launch Q1" (shared with the product marketing manager, so project-only by default). Each had the same fact sheet. Custom instructions held only personal style rules.

When the pricing page changed, they updated one fact sheet and re-uploaded it to all three. Within a week a draft in "Brand content" still quoted the old tier name; the Sources line showed it came from a saved memory. They deleted that memory.

## What should you check before the next lesson?

- Write custom instructions under 1,500 characters that say nothing about a specific brand.
- Create one brand project with instructions, a fact sheet and a voice guide.
- Decide which projects need project-only memory and which need ChatGPT Work.
- Claude users can compare with [Claude projects and brand voice](https://mentionx.ai/learn/claude/claude-projects-brand-voice).

Next: [Custom GPTs, plugins and skills for your team](https://mentionx.ai/learn/chatgpt/custom-gpts-plugins-skills-marketing-teams). Or return to the [ChatGPT for Marketers track](https://mentionx.ai/learn/chatgpt/chatgpt-for-marketers).

## Common questions

**What is the difference between custom instructions and memory in ChatGPT?** Custom instructions are rules you write that apply to every chat. Memory is context ChatGPT picks up from past chats, saved memories and other sources. Use instructions for stable preferences and check memory regularly.

**Do project instructions override custom instructions?** Yes. OpenAI says project instructions apply only inside that project and override your global custom instructions.

**Should a client project use project-only memory?** Usually yes. Project-only memory stops chats in that project from drawing on chats elsewhere, and vice versa. Shared projects use it automatically. Note that ChatGPT Work is not available in a project-only memory project.

## Sources

- OpenAI Help Center, [ChatGPT Custom Instructions](https://help.openai.com/en/articles/8096356)
- OpenAI Help Center, [Projects in ChatGPT](https://help.openai.com/en/articles/10169521)
- OpenAI Help Center, [Memory in ChatGPT](https://help.openai.com/en/articles/8590148)
- OpenAI Help Center, [Temporary chat in ChatGPT](https://help.openai.com/en/articles/8914046)
All accessed 4 Nov 2026.

## Frequently asked questions

### What is the difference between custom instructions and memory in ChatGPT?

Custom instructions are rules you write that apply to every chat. Memory is context ChatGPT picks up from past chats, saved memories and other sources. Use instructions for stable preferences and check memory regularly.

### Do project instructions override custom instructions?

Yes. OpenAI says project instructions apply only inside that project and override your global custom instructions.

### Should a client project use project-only memory?

Usually yes. Project-only memory stops chats in that project from drawing on chats elsewhere, and vice versa. Shared projects use it automatically. Note that ChatGPT Work is not available in a project-only memory project.

---

Written and reviewed by Dipuck Jones for MentionX Learn. The HTML version of this page: https://mentionx.ai/learn/chatgpt/chatgpt-custom-instructions-memory-projects