$66 in month one, $41,000 a month six months later: one AI-written guide a day

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.

A ChatGPT dot is not a longer chat. It is an always-on agent that keeps working between conversations, lives on its own cloud computer and can reach connected apps without you sitting in the window. OpenAI launched dots on 29 September 2026, powered by GPT-6 Astra, and they are rolling out gradually. The interesting part is not that it can do work alone. It is how much of that work you define before you let it start.

Access is narrower than the launch headlines suggested. OpenAI lists dots for Pro 100, Pro 200 and Pro 500 users over 18 outside the European Economic Area, the United Kingdom and Switzerland, for Business Premium worldwide, and for Enterprise as a beta that a workspace admin has to switch on. Free, Go, Plus and standard Business plans are not on the list. If you are eligible, the dot can be created in the ChatGPT mobile app, desktop app or a desktop browser; mobile web is not supported.

Here are the six parts worth setting, in the order they matter.

1. Give it one ongoing job

The first mistake is treating a dot like a search box. OpenAI's own guidance is to hand it work you want it to keep track of: a project, a recurring research brief, a queue of requests. Describe the outcome, share the sources it should use, and say which decisions must come back to you. A narrow job with a clear finish line is easier to check than a vague instruction to "handle my work".

2. Connect only the apps it needs

During setup you can connect plugins for email, calendar and files, or skip that step and add them later. Add the one or two services the job actually requires. A Slack connection does not grant access to your inbox, and adding a dot to a channel does not make it monitor that channel. Each connection is separate, so treat every plugin as a new key rather than part of the same login.

3. Choose where it reaches you

You can message or call a dot in ChatGPT, and reach the same dot in Slack or Microsoft Teams. Changing the channel does not create a new dot or reset its memory. Tell it where different updates should go: routine progress in ChatGPT, a decision that needs you in Slack. If you add it to a team channel, say which channels and events it should watch. Being present is not the same as being on duty.

4. Write the rules before it acts

Custom rules are optional, but they are the part that turns a general instruction into a boundary. On desktop and web they sit under Settings > Personalization > Custom rules; on mobile, under Customize > Custom rules. Each rule offers four behaviours: take the action without asking, take it when you say so, ask before taking it, or hand it back to you. Use "ask" for anything customer-facing and "hand off" for deleting shared files or changing account details.

Rules are instructions the dot tries to follow, not a permission system. OpenAI warns that a rule can make mistakes, and it cannot grant access to an app, override built-in safety checks or skip a required sign-in. Setting a rule is not the same as connecting the account.

5. Watch Activity and approve the risky steps

In the desktop app, Activity shows a task's progress, files, results and any background work. It also surfaces requests waiting on a decision, an app connection, a sign-in or an approval. Before a dot acts on your accounts or shares information, an automatic review checks the action against your instructions, permissions, custom rules and built-in safety. Some steps, such as changing a password, are handed back to you by design.

6. Know what Pause actually stops

Pause stops the dot's current main task. It does not stop every delegated task and it does not cancel future scheduled runs. Those have separate controls: open a delegated task in Activity to stop it, and open Scheduled to disable or delete a recurring job. Deleting the dot is permanent and does not undo changes it already made in connected apps or messages it already sent. Decide what you would need to reverse before you give it something irreversible.

The limits

Dots can make mistakes, and the rollout is gradual, so an eligible plan may still show nothing for a while. Dot conversations do not count toward ChatGPT usage limits, but work the dot starts in Work or Codex counts toward those products' limits as usual. OpenAI says it does not train on Business, Enterprise or Edu workspace content by default. None of that makes an always-on agent a good place for passwords, payment details or anything you would not put in a shared document.

What to try first

Pick one recurring job you already do by hand: a weekly competitor brief, a triage list for a shared inbox, a status update pulled from project files. Connect only the sources it needs, keep approvals on for anything that leaves your account, and run it for a week before adding a second job. The point of the six parts is not to make the dot more powerful. It is to make its power visible.