The anatomy of a ChatGPT dot: 6 parts to set before it works alone

A self-taught filmmaker spent six years directing, editing and building 3D scenes for clients abroad. When generative AI turned that craft into something anyone could buy in seconds, his own creative work dried up. Instead of fighting the change, he built a tool around it.

The product is an all-in-one AI creative workspace: one place to write, generate images, turn them into video, add music and voice, and keep projects, consistent characters and team credits together. He built it alone, with no programming background, no outside funding and no paid ads. He says it brings in about $60,000 a month, roughly ten months after launch.

The interesting part is not the product. It is how he got customers, because his first viral success made almost no money.

59 million views, almost no revenue

He made a series of short AI videos styled as phone footage of famous scenes, the kind of thing a bystander might have filmed. In 30 days the series did 59 million views on Instagram and added more than 200,000 followers across his account and the product's account.

That is the number most people would stop at. He says it barely moved revenue. Views are attention, not intent: someone who watches a spectacular clip has no reason to open a tool, let alone pay for one.

The post that changed it

What worked was a tutorial published after the series. In it, he showed exactly how one of the videos was made and opened the entire project for anyone to copy: every prompt, every generated image, every video take. Nothing was hidden behind a paywall or a course.

The effect was immediate. On the day the tutorial went live, signups from outside his home market jumped 6.5 times. Over the next three weeks, 3,285 people signed up, about 78% of all new signups in that period.

He calls the loop "show, then teach": make something people actually want to watch using your own product; post only the result, with no pitch and no feature list; then immediately teach exactly how you made it, with the files open.

The logic is simple. The result earns attention. The tutorial converts it, because the viewer has just seen proof that the thing is possible and is now given the recipe. Giving the recipe away also builds more trust than claiming the tool is clever.

The second channel: affiliates

Customers who run the same loop on their own audiences earn a share of what they bring in. He says one affiliate brought in more than $30,000 on his own. That is a distribution channel built from people who already use the product, not from an ad budget.

How to copy the method

Start with a result, not a product page. Pick something your tool can make that is visually obvious in a few seconds: a transformation, a before-and-after, a scene that should be impossible. Make it with the tool yourself, because the demonstration has to be real.

Post the result by itself. No introduction, no list of features, no link. If the result needs an explanation to be interesting, it is not the right result yet.

Then post the recipe. Show the screen, the prompts, the settings and the mistakes. Open the project if the platform allows it. The tutorial should let a motivated viewer reproduce the result without guessing.

Repeat the pair. The result finds new people; the tutorial turns some of them into users. Over time the tutorials become a searchable library that keeps working after the views fade.

Finally, let your best users teach it too. An affiliate or referral deal gives them a reason to run the same loop for their audience, and it costs nothing until a sale happens.

What to watch out for

Every number here is self-reported in a promotional case-study interview and has not been independently audited. The $60,000 is revenue, not profit; AI image, video and audio generation costs money on every run, and the interview does not break out margins.

He also had advantages that are hard to copy: six years of professional visual skill, an existing audience, and a product built specifically around his own workflow. The method is teachable; the timing and the craft are not guaranteed.

And the central warning is his own: he says his biggest mistake was thinking virality is a business. Millions of views felt like success, but they barely moved revenue until he gave people a reason to act.

The takeaway for anyone selling an AI service or tool is uncomfortable but useful. A demo can get you seen. Only a clear, copyable path from the demo to the result gets you paid.

ChatGPT's memory is not one file. OpenAI's help centre says memory can draw on past chats, saved memories, custom instructions, files in Library and connected apps such as Gmail. The screen called the memory summary is only a high-level view, and OpenAI says it may omit details that are less relevant or come from sources it does not display individually. So the first move is not deletion. It is asking what the assistant thinks it knows, where each line came from, and what the summary left out.

That matters because the controls are split up. A saved memory and the chat that produced it are stored separately. A quiet button that stops the assistant mentioning something is not a delete button. And memory is not the same setting as model training. Getting those three distinctions right is most of the job.

Where the controls are

Open Settings, then Personalization, then Memory. Depending on your plan, region, platform and workspace, you may see Memory, Reference saved memories, Reference chat history, Memory summary, Manage or Saved memories. If a control described here is missing, OpenAI says it may not be available for your account yet. Workspace owners can also limit these settings for managed accounts.

Three distinctions that matter

First, "Don't mention this again" reduces future references to a detail. It does not delete the original chat, file, email or memory. Second, deleting a chat does not necessarily delete a separate saved memory created from it, and deleting a saved memory does not remove the chat where you shared the information. You may also need to remove it from Library files or a connected app. Third, memory controls are separate from training. The training switch is under Settings, then Data controls, and is called Improve the model for everyone. Turning it off stops new conversations being used for training, but it does not delete or hide saved chats.

The five prompts

We ran each prompt once in a clean chat and kept the five that returned a usable, specific answer. Paste them one at a time. Start with the audit, because you cannot correct a list you have not seen.

**1. Audit the list.** This asks for a table of memories, the model's confidence and a source, and forces an honest "unclear" when it cannot trace one. Treat the confidence column as the model's own estimate, not a fact.

List everything you remember about me in a table: what you remember, how confident you are, and where it came from. If you cannot name the source, write unclear. Mark anything I never confirmed.

**2. Correct the wrong lines.** This turns a correction into a replacement memory and asks for the exact place to paste it, so you are not leaving the old line in place beside the new one.

Here is what you got wrong about me: [old detail] should be [correct detail]. Rewrite it as one short memory in my voice, then tell me where to paste the correction and what it replaces.

**3. Prune both copies.** This sorts the list and, for each removal, names the chat, file or app you must also clear. That follows OpenAI's own warning that the saved memory and its source are stored separately.

Sort my memories into keep, fix and remove. For each remove, give me the settings path to delete it and the chat, file or connected app I must also delete, because the saved memory and the source are stored separately.

**4. Quiet what you want kept but not used.** For details that are true but sensitive, this writes the "don't mention again" line and states plainly what it does not delete, so you are not mistaking silence for removal.

These details are true but I do not want them used again: [detail]. Write one 'don't mention again' line for each, then list what that changes and what it does not delete.

**5. Keep a clean brief for temporary chat.** A temporary chat can be started unpersonalized, which means it does not use your memories or custom instructions. You choose personalized or unpersonalized before the conversation starts and cannot change it afterwards. This prompt gives you a short brief so the task still works without your profile.

Turn this into a 120-word brief I can paste into an unpersonalized temporary chat: [task, deadline, audience, constraints]. Leave out my name, contact details, employer and anything about money or health.

What we cut

Prompts that asked the model to "find every hidden data point" were cut, because the model cannot see storage beyond the sources OpenAI lists. Prompts that asked it to invent a source were cut for the same reason. The five above ask only for what the product exposes: the memory list, the sources panel and the settings paths.

The limits

The memory summary may leave out details, and a Sources panel may not show every factor behind a response. Deleted saved-memory logs may be retained for up to 30 days for safety and debugging. If you turn off Reference chat history, information remembered from past chats is scheduled for deletion within 30 days, but the original chats stay in your history unless you delete them. Temporary chats do not create memories and are not used to train models, but they may be kept for up to 30 days for safety. Self-service data export is available to signed-in Free, Go, Plus and Pro users, not to Business, Enterprise or Healthcare workspaces. A memory toggle also does not disable limited safety uses of context in rare, high-risk situations.

What to do now

Open the memory settings and ask for the audit. Correct the lines that are wrong, then delete the ones you do not want, then clear the chats, files and apps behind them. If you only want the detail ignored rather than deleted, use the quiet line and remember it is not a delete. Turn off model training in Data controls if you have not already. For the next sensitive task, start an unpersonalized temporary chat and paste the brief.