How to Write ChatGPT Prompts: Keep the Goal, Material, Requirements, and Tone Separate
According to official prompting guidance, a prompt should at minimum state what needs to be done, which materials to rely on, what form the result should take, and what tone to use. When an answer is unsatisfactory, adjust it item by item against these categories rather than rewriting the whole thing or judging the prompt on a single result.
When writing a ChatGPT prompt (the text you send to the model), first separate four things clearly: what needs to be done, which materials to rely on, what form the result should take, and what tone to use. When an answer is unsatisfactory, revise it item by item along these lines.OpenAI's prompting guidance for ChatGPT lists "be clear, be specific, provide enough context, and avoid ambiguity" as basic practices, and describes prompt engineering (designing and refining the input so the answer moves in the direction you want) as an iterative process rather than something you get right in one pass. A separate API prompt engineering document adds a premise that is often overlooked: model output is non-deterministic (the same input is not guaranteed to produce exactly the same result every time).
What four things should a prompt cover at minimum
Goal. Start with a verb and state who the finished result is for. "Take a look at this material for me" becomes "Compress this material into three points for reading aloud at a meeting," and the model knows what to do.
Material. Paste it directly into the conversation and explain how to handle what is missing, for example "mark anything not written down as 'to be confirmed' and do not fill it in yourself."
Result format. State the length, the structure, and the items that must appear. Being clear here saves you from repeatedly asking for "more revisions" afterwards.
Tone. Put it on its own line, using specific adjectives.
Suppose you want to turn a set of notes into a meeting notice. You could write:
Goal: Turn the notes below into a meeting notice for colleagues.
Material: Use only the information in the notes; mark anything not written as "to be confirmed" and do not fill it in yourself.
Result format: Within 200 characters, in four points, covering the time, place, topics, and what each person should prepare.
Tone: Formal and concise.
Notes: Wednesday 3 p.m., third-floor meeting room, discussing next quarter's schedule, Xiao Li to prepare the data.
The most direct benefit of writing them separately is that when the result is wrong, you can pinpoint which line is at fault instead of rewriting the whole thing.
Why the tone should be written as specific adjectives
Official guidance points toward using descriptive adjectives to specify tone, with examples including formal, informal, friendly, professional, humorous, serious. Phrases like "write it more professionally" or "make it more natural" do not point to a specific style, so the model can only guess. Replace them with one clear adjective and add a sentence with the example you want, and you have far more room to compare and judge.
One thing to note: this approach addresses whether the model can understand your requirements; it does not mean the content is necessarily accurate. For facts, numbers, and times, you still need to check them against the original source yourself.
When the answer is wrong, first work out which category of problem it is
Official guidance lists iterative improvement as a basic practice: give a first draft, look at the answer, then adjust the wording, add context, or simplify the request based on the output. In practice, change only one thing at a time and attribute the problem to one of three categories:
The goal is too vague. The answer is broad and generic, or misses the point. Replace the request with a verb plus a purpose, for example "compress it into three paragraphs for reading aloud at a meeting."
The material is not in the prompt at all. Just replying "be more accurate" will not change anything. Paste the original text or data in first, and note which fields must be preserved.
Two requirements pull against each other. You want it finished in one sentence and also want every detail covered. Split it into two steps: list the key points first, and after you confirm them, compress.
Change three or four things at once and even if the result improves, you cannot tell which one made the difference, and with a different type of task you have to start experimenting from scratch.
Different models call for different emphasis in how you write
Official documentation distinguishes two types of models: reasoning models generate a thinking process internally, are good at complex tasks and multi-step planning, but are generally slower and more expensive; another type of model aimed at general text is faster and cheaper, but depends more on you stating the execution requirements explicitly. The documentation also notes that different model types, and even different versions in the same series, may perform differently on the same prompt.
In terms of how you write: for tasks that require multi-step judgment, spell out the steps and the decision conditions; for tasks like rewriting, compressing, or translating, getting the format and boundaries clear is usually more important. When someone says "this prompt works well," it only means it works at their entry point; it cannot be taken directly as a conclusion that it applies to yours as well.
There is a boundary to draw here: the instructions parameter, the developer and user message roles, fixed model versions, and test and evaluation suites in that document are concepts intended for developers building applications with the API (an application programming interface, a service that lets programs call the model). The ChatGPT chat window does not have these switches, so do not treat "setting a developer role" as something you do in chat.
A few recurring mistakes
Cramming five or six requirements into one paragraph, so when something goes wrong there is no way to start, and it is hard to judge which sentence to change.
Using "make it more professional" or "make it more detailed" instead of adding material, when the problem is actually the material, not the wording.
Asking for both brevity and complete coverage, two conditions that conflict in themselves.
Judging "this prompt doesn't work" on the basis of one unsatisfactory answer. Output itself involves randomness, so it is worth trying two or three times to see whether it consistently deviates from your requirements.
Treating the background in your own head as information the model already knows, then blaming the answer for being inaccurate when it was never written into the prompt.
Writing prompts does not require memorizing templates; what it requires is breaking the requirements apart and changing only one thing at a time. If you are using it for the first time, you can start with the free plan beginner's guide and practice on a small task that is easy to check.
A GPT version number is a model name; it is not the same as the list your account can actually call. Which models you can use is decided jointly by your plan tier, whether the model has been retired, and the allowance available at the time: older models such as 4o are being retired, Go does not include older models, Think uses GPT-5.6 Luna, and only Pro 500 includes Ultrafast. Always verify against the model picker.
Compared with the free version, Plus adds broader access to models and tools, higher limits, priority during peak periods and advanced reasoning; however, model availability and limits can change, and message caps may still apply. API usage, annual billing and extra allowance are not included. The article sets out the order for checking an account's actual permissions with the model picker and the account page.
Projects places related conversations, files, and instructions into a single workspace so later conversations continue with the same context. Based on the official documentation, this covers the setup steps, the scope of project instructions, file limits and duplicate file handling, and the permissions, memory, and deletion boundaries of shared projects.
Where you check your ChatGPT renewal date depends on where you subscribed: web subscriptions in your account settings, Apple in-app purchases in the system subscription list, Google Play on the Play Store subscriptions page, and self-serve Business in the workspace billing page. This article distinguishes the next charge date from the expiration date, gives the lookup steps for each channel, the 24-hour cancellation cutoff, and the order to troubleshoot in when you cannot find the date.
According to the OpenAI official supported countries list verified on 2026-11-20, Hong Kong is not included. The official rule is that the API is unavailable in locations outside the list, and access from outside the list may result in an account being banned or suspended. This article shows Hong Kong users how to check eligibility in three layers — official list, network exit, account status — and explains the order in which to handle a regional error and why a proxy is not a solution.
ChatGPT Business is OpenAI's self-serve ChatGPT workspace plan for teams, priced per seat: a minimum of 2 seats, with Standard seats at 25 USD per person per month on monthly billing or 20 USD per person per month on annual billing, and Premium seats at 125 USD per person per month on monthly billing or 100 USD per person per month on annual billing; API usage and credits beyond the included allowance are billed separately.
Gemini's cost is a subscription fee charged through Google One storage membership and Google AI plans. Every account starts with up to 15GB of free storage, paid tiers start at 100GB, and Google AI plans with AI features start at 200GB. Tiers are based on storage capacity and billed monthly or annually, and the final amount is determined by the tier, the billing cycle, and the billing location. This article checks the storage and availability of each tier and the steps to upgrade, change, or cancel. It also explains the ChatGPT top-up path that readers in Hong Kong and Taiwan can complete with Alipay or WeChat Pay.
The ChatGPT registration region restriction is a rule under which OpenAI only allows users to register accounts and create API keys in countries or regions on its official supported list. This article explains what error you see when registering outside the list, how OpenAI determines the registration region, and why phone number or identity verification must be completed by the account holder. It also sets out the boundary of our top-up service: we handle payment only, not registration or verification.
ChatGPT subscription fees are non-refundable by default. Only a few exceptions may be approved: billing errors confirmed by OpenAI, verified unauthorized charges, documented service or access failures, and an unused individual subscription within 7 days that meets the conditions. The EU, UK, Turkey, South Korea, and Brazil also have statutory refund rights. Accidental purchases, forgetting to cancel, dissatisfaction, and switching plans are not, in themselves, grounds for a refund. This article sets out, by channel and region, the situations in which you can and cannot apply.
Netflix bills monthly only, with no annual plan. Based on the Hong Kong page verified on 2026-11-18, the three ad-free tiers cost HK$78 (Basic), HK$98 (Standard) and HK$118 (Premium) per month, and each extra member costs HK$31 per month. If you only want 4K for yourself, the official service sells you a whole household with 4 slots, whereas our Hong Kong Premium 4K shared slot sells a single position for ¥33 per month and accepts Alipay and WeChat Pay, which is better suited to one person's own use.
MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources; it solves the problem of manually copying and pasting data from tools into the AI. This article explains what it is for, gives the four commands for adding, checking, using, and removing a server in Claude Code, a comparison table of the four connection methods, and the troubleshooting order when a connection fails. It closes with how readers in Hong Kong and Taiwan can complete the payment step for AI tool subscriptions using Alipay, WeChat, and RMB.
An AI Agent is an AI program that can break down a task itself, call tools and work through multiple steps until the job is done, which is quite different from a chatbot that only handles one question and one answer. This article explains the difference and a three-step way to tell them apart, gives the steps for anyone to start using their first agent, and explains how readers in Hong Kong and Taiwan can subscribe to ChatGPT with Alipay or WeChat when they have no usable foreign-currency credit card.