MMOOZZGG.com

Guide

Custom GPT after 11 December 2026: how to build an AI agent in ChatGPT step by step

Medium12 min read12 sources

If you planned a custom GPT, build a skill in a ChatGPT plugin instead: instructions, files, minimal app rights and a 10–15 prompt test. OpenAI retires these GPTs on 11 December 2026, Virtualization Review reported on 28 September 2026; timing can vary by account. Below are six steps, the move of an existing GPT and data checks for companies in Russia. My rule: build only what you can carry out of ChatGPT.

Custom GPT after 11 December 2026: how to build an AI agent in ChatGPT step by step
On this page · 11 sections

What you need and how long it takes

By my estimate, not a measurement, creating a working assistant in ChatGPT takes about two days. That is one evening for the task and the skill, and one more day for testing and fixes. You end up with an assistant that does one task and has passed a set of test prompts. I checked the interface against OpenAI’s help pages on 20 November 2026; they carry no publication date, so the sources show the check date.

  • A ChatGPT account on a plan that has the features you need: the table below shows what is where.
  • Reference documents: your rules and templates, plus two or three samples of good work a person did before.
  • A list of the services the assistant will work with, and the rights for each: read only, or read and write.
  • 10–15 real requests from colleagues or customers: step 5 turns them into your test.

The ChatGPT pricing table, checked on 20 November 2026, shows which features each plan provides.

FeatureWhere it is, per the pricing table on 20 November 2026
Projects and skillsFree, Go, Plus and Pro
Create and share pluginsGo, Plus and Pro; not on Free
Share a plugin with a workspace from a personal planPro only
Developer mode (beta) for a custom MCP serverPlus and Pro
Scheduled tasksGo, Plus and Pro
Workspace agents, research previewBusiness, Enterprise, Edu and Teachers
Plugin data not used for training by defaultBusiness, Enterprise, Edu and Teachers; on personal plans you opt out in settings

Which path to take now: a GPT, a plugin or a workspace agent

It is too late to build a new GPT: OpenAI retires user-built GPTs on 11 December 2026, Virtualization Review reported on 28 September 2026. The outlet cites OpenAI’s announcement of 11 September 2026 and adds that timing can vary by account. OpenAI’s own announcement is not among my sources, so this date and the ones below follow the outlet. When you try to create a GPT, the interface now offers to make a plugin instead.

A GPT is a personalized ChatGPT, configured with your instructions, knowledge files, apps and actions; the section on moving GPTs shows what a plugin keeps. According to OpenAI’s developer documentation, a plugin holds skills, an MCP server, or both. A skill is a set of instructions and materials for a repeated task; an MCP server adds tools and a connection to outside systems. ChatGPT and Codex use one plugin directory.

Here is my choice. One person needs only a skill inside a plugin: instructions plus reference files. You need an MCP server only when the assistant needs live data or actions in your systems. OpenAI itself advises starting with the simplest form and adding a server later.

A team on Business should look at workspace agents. The OpenAI Cookbook describes a workspace agent as a shared assistant. It runs on a schedule, keeps a memory and gets its rights from an admin. From here on I call it a team agent.

If you are still choosing between ChatGPT, Claude and an open model, start with our analysis of which agent platform to choose. This guide stays inside ChatGPT.

Step 1. Describe one task and the result that closes it

Step 1 gives you one task on one page and 10–15 requests for it. Take the fields from the use-case inventory in OpenAI’s help, checked on 20 November 2026.

  1. Write the user’s goal in one sentence, for example: prepare a supply contract summary for the CFO.
  2. Collect sample requests, direct and indirect. Take them from tasks your team already does, from support requests and from workarounds where people copy data between programs.
  3. Describe the expected result: which document, which parts, what length.
  4. List the context and access: which files and services the assistant must see.
  5. Draw the safety line: can the task expose data, change a record, spend money or affect another person.
  6. Decide on each use case: support it now, defer it or exclude it on purpose.

I advise starting narrow. As I put it in my talk AI Won’t Take Your Job (2025), start with “an agent that does some niche task” (translated). In my view, most so-called agents are a slightly improved prompt, and that is enough for a first task.

Step 2. Write the skill instructions

The fastest way to create a skill is the built-in helper @skill-creator, per OpenAI’s help checked on 20 November 2026. You give it the goal and the tools you need. You can also write the skill files by hand.

Per the OpenAI Cookbook, a team agent is built under Agents with Create and Create agent. After the builder’s plan, click Build this agent, or pick a template in Browse templates.

Per OpenAI’s help, the body of the instructions answers six questions:

  1. What input to expect: for example, a contract as a PDF and a manager’s question.
  2. Which steps to take, and in what order.
  3. What the result looks like: sections, length, tone.
  4. Which facts not to invent: amounts, dates and clause numbers come only from the document.
  5. When to ask a question, stop or refuse.
  6. Which reference files to read, and when.

Here is a short instruction for a contract summary: “Find the parties, the subject, the amount, the deadlines, the penalties and the termination terms. Give every figure with its clause number. If a clause is missing, write ‘not found’ and do not guess. If the file is not a contract, say so and stop.”

Don’t put the value into the prompt’s wording: I once built an assistant to phrase my requests and thought it a real find. As I said in the podcast Has AI Made School Obsolete? (2025), “within literally 3–4 months it became built in” (translated). Your instructions hold up because of your company’s workflow and data, not a clever phrase.

Result of this step: the skill turns on for a direct request from step 1 and answers in the right form.

Step 3. Add reference files and decide what must stay out

Long material goes next to the instructions in three folders, not inside them, per OpenAI’s help checked on 20 November 2026. Rules, examples and reference text go into references, templates into assets, and calculations into scripts.

If you have more than a handful of documents, explore how an agent that answers from company documents works.

Do not upload two kinds of data to the reference files. First, personal data of customers and staff, until you settle how it crosses borders; the section on Russia below covers this. Second, trade secrets on personal plans, unless you have opted out of training.

Step 4. Connect apps and give minimal rights

Through a plugin, ChatGPT sees only what you already see in the connected service, OpenAI says on its plugins page, checked on 20 November 2026. So configure rights for the task, not just in case.

  1. Explore plugins in the ChatGPT sidebar or at chatgpt.com/plugins and connect the service. In a chat, use @ and its name to call it.
  2. Check who turns plugins on: the admin in Enterprise and Edu, on by default in Business, and you yourself on Plus and Pro. OpenAI’s page on them does not name Go, though the pricing table says you can create them there.
  3. For a team agent, choose the connection for each app. Use each user’s own (End-user account) for mail and calendar, and a common one (Agent-owned account) for a shared folder.
  4. Turn on only the actions you need, like reading the calendar but not adding events. Leave delete, sharing and other changes off.
  5. Make sure the assistant asks for confirmation before it saves or changes anything: for team agents this is the default, per the OpenAI Cookbook.

Your own MCP server for a CRM or accounting system needs developer mode (beta), which the pricing table lists on Plus and Pro. You add it under Plugins: the plus button, then Add custom MCP server. The pricing table does not list this mode on Business or Enterprise, so ask your OpenAI account team before you plan a server. What this server is and who writes it is covered in our guide on how to connect company services through MCP.

The main risk here is prompt injection: a foreign command hidden in an email or a document the assistant reads. OpenAI advises assuming such input will reach your server and requiring a human’s confirmation for actions you cannot undo. How to defend against it is explained in our piece on prompt injection.

The second risk is a shared connection. Anyone who can run a team agent also uses its shared account, the OpenAI Cookbook warns.

Besides agents, you need infrastructure, you need security. (translated)

Mike Mozgfrom my talk From Successful CTO to YouTube (2025)

Step 5. Test the agent on a set of prompts

Testing runs on the 10–15 requests from step 1, sorted into the five types from OpenAI’s help, checked on 20 November 2026. For an assistant with apps, add follow-ups and write actions.

Request typeExample for a contract summaryWhat should happen
Direct“Summarize this supply contract”The skill turns on and provides a summary in the template
Indirect“What do we risk if the supplier is late?”The skill turns on, the answer cites the penalty clauses
Incomplete“Look at the contract”, with no fileThe assistant asks a follow-up question
Off-topic“Write a birthday note for a colleague”The skill stays off
Edge caseA contract with no penalty clauseIt answers ‘not found’ and invents nothing
Follow-up“Now compare it with the last summary”It uses data from the previous answer
Write action“Save the summary to the shared folder”It asks for confirmation before writing

For each request, record what turned on, what was done, which errors came up and whether the assistant asked for confirmation.

Test the content too, not only the behavior. In my experience, models invent laws and court cases. As I said in the podcast Digital Slaves (2026), “lawyers then actually go to court and show it” (translated). Check every reference to a law or a case against the original.

A full test method with metrics and a log is in our guide on how to test an AI agent.

Step 6. Run it on a schedule and share it with the team

A team agent is published with the Create button, per the OpenAI Cookbook checked on 20 November 2026. By the same source, each change goes out as a new version with Update.

  1. Open Automations in the published version, channel ChatGPT.
  2. Set the days, time and task, then click Add automation.
  3. Check the first run for stuck confirmations and failed actions.

Per the OpenAI Cookbook, a schedule runs on behalf of its creator, so you answer for what it does.

Per the OpenAI Cookbook, Share opens access: Can chat lets people run the agent, Can edit lets them publish versions. Your admin allows sharing; check the shared account’s reach first.

If you already have a custom GPT: move it before 11 December 2026

An existing GPT moves into a plugin from the My GPTs section, if migration is turned on for your account. That is how Virtualization Review described it on 28 September 2026, citing OpenAI. If My GPTs shows no option to migrate, the move is not available for your account yet: rebuild from your copies by steps 1–5.

What the GPT hadWhat you get after the move
InstructionsThey become a skill of the plugin
Knowledge filesThey are copied into reference files
Connected appsThey can be moved
Custom ActionsNot moved: create them again with an available app or a custom MCP server
Selected modelNot moved
Past conversationsNot moved
User accessNot moved: the plugin starts private, and you share it again

After the move, run the test set from step 5. OpenAI warns that the plugin may answer differently from the GPT.

Data and access from Russia: what to check before the first run

OpenAI warns that using its services outside its list of countries may get an account blocked or suspended. Russia is not on that list, per OpenAI’s documentation checked on 20 November 2026. So an assistant that a company process depends on can vanish together with the account.

The second issue is personal data: if it reaches the assistant, that is a cross-border transfer. Before the transfer, the operator must notify Roskomnadzor, Russia’s data protection regulator, under Part 3 of Article 12 of the personal data law (152-FZ). The notice covers only the transfer abroad and does not replace the law’s other rules on how a company collects and stores data. The part numbers follow the edition of 26 July 2026.

The notice provides the legal basis and purpose, the data and its categories, the categories of data subjects and the countries (Part 4). It also gives the date the operator assessed how the foreign recipient protects the data, so the assessment comes first. The regulator decides on the notice within 10 working days (Part 9). Until then, data may not go to countries outside the list with adequate protection (Part 11).

If the transfer is banned or restricted, the operator must make sure the data already sent is destroyed (Part 14 of Article 12). I checked the article’s text on ConsultantPlus, a Russian legal database, on 20 November 2026. The page also notes that a newer edition, with amendments not yet in force, has been prepared.

AI solutions are often built by people without the right training. As I said in the podcast Digital Slaves (2026), “they break the law, and they break it seriously” (translated). For OpenAI’s status, the risks and the alternatives for companies, see our article on the OpenAI API for business.

Common mistakes and how to tell the agent is ready

The assistant is ready when three conditions are met. It passed the whole set from step 5 with no invented facts and no extra actions. The first scheduled run went through without errors, and a copy of the instructions and files is stored outside ChatGPT. In my experience, the three mistakes below come up more often than any others, and each shows a sign you can catch before launch.

MistakeSignHow to fix it
One skill for every task in the departmentAnswers mix up the tasksSplit skills by trigger and success criteria
Write and delete without confirmationThe assistant changes data on its ownTurn delete off, keep confirmation on
Testing with two lucky questionsColleagues find the errors after launchThe full set from step 5 after every update

An assistant in ChatGPT does not fit when you need live data from an accounting system, personal data, or a process that money depends on. Then you build it outside ChatGPT. For a first try on any platform, our lesson on a first AI agent in one evening will do.

My advice to beginners is the one I gave in the podcast Has AI Made School Obsolete? (2025): “make your own mini agents” (translated). A narrow assistant with an honest test teaches more than any course.

Questions and answers

Can I build an AI agent in ChatGPT for free?

Partly: the pricing table lists projects and skills on Free, so you can write and test a skill there by steps 1–3 and 5. Packaging it in a plugin starts with the Go plan, since Free cannot create or share plugins. Scheduled tasks also start with Go, and team agents exist only in Business, Enterprise, Edu and Teachers. That is what the ChatGPT pricing table showed on 20 November 2026.

What happens to my GPT and its links after 11 December 2026?

The GPT stops working on that date, though timing can vary by account. People you shared the link with do not get access to the new plugin on their own: you share it again. That is what Virtualization Review wrote on 28 September 2026, citing OpenAI.

How is a workspace agent different from a plugin?

Per the OpenAI Cookbook, a workspace agent has a memory: a separate folder with notes and results, and in ChatGPT each user has their own. The ChatGPT page on workspace agents says the admin decides who builds them and which actions they may take. The same page says audit logs show what happened.

Can I sell my ChatGPT agent to other companies?

Yes: per the ChatGPT page on plugins, you can submit a plugin for review, and once approved, other users can find it in the directory. I would not build a business on that: in the podcast Has AI Made School Obsolete? (2025), I called selling prompt-only agents “for me just another info-business hustle that won’t live long” (translated). The value lies in a company’s data and workflow.

Sources and fact-checking

Mike Mozg’s quotes and views, translated from Russian: From Successful CTO to YouTube (2025, https://www.youtube.com/watch?v=ixG7_zxdM2o). AI Won’t Take Your Job (2025, https://www.youtube.com/watch?v=KqwVcJnluT4). Has AI Made School Obsolete? (2025, https://www.youtube.com/watch?v=gEpobOkAuKc). Digital Slaves (2026, https://www.youtube.com/watch?v=NHtRIawMlLo). The End of Marketplaces! (2025, https://www.youtube.com/watch?v=SsU9C9PwuFg). Checked by the editors on 20 November 2026.

  1. Plugin architecture (developers.openai.com)
  2. Build skills (developers.openai.com)
  3. Connect and test your plugin (developers.openai.com)
  4. Brainstorm plugin use cases (developers.openai.com)
  5. Security & Privacy (developers.openai.com)
  6. Supported countries and territories (developers.openai.com)
  7. Building workspace agents in ChatGPT to complete repeatable, end-to-end work (raw.githubusercontent.com)
  8. Scale your team with workspace agents (chatgpt.com)
  9. Plugins in ChatGPT (chatgpt.com)
  10. ChatGPT Pricing (chatgpt.com)
  11. OpenAI to Retire Custom GPTs, Replace Them with Plugins (virtualizationreview.com)
  12. Article 12. Cross-border transfer of personal data (consultant.ru)

Found a mistake? Tell us

Publications

Mike Mozg

Anthropic IPO raises $81.34 billion and makes its compute costs public

The Anthropic IPO raised $81.34 billion, and trading on Nasdaq began on 19 November 2026, the Russian business daily RBC reported. That beats SpaceX's base IPO, but it becomes a record only once the agreed $26 billion private placement closes. I don't read this as market news: Anthropic's public filing shows what compute costs a frontier AI lab. In my view, it shows where prices, limits and access

News6 min
Contact us