Codex Tutorial: Choose the Right Entry Point and Complete Your First Project Task
Tell apart the desktop, web cloud, command line, and editor entry points, sign in along the official path, provide project context, start with a small task that has a clear scope, then check the results.
When using Codex (OpenAI's coding assistant) for the first time, choose an entry point based on where you work: start local projects from the desktop app, and use a cloud environment for remote coding tasks. After signing in, provide the files or context the task requires, and begin with one small task that has a clear scope and results you can verify.
How do I choose between the web, command line, and editor entry points?
Desktop app: Suited to local projects; it can read and modify files in the folder you select.
Web cloud: Suited to remote coding work; you can select or create a Codex Cloud (cloud runtime environment).
Codex CLI (command line tool): Suited to developers who are used to working in a terminal.
Codex IDE extension (code editor extension): Suited to developers who want to stay inside their editor.
Just pick one entry point and complete the task. The instructions below focus on the desktop app; for installing the command line tool and the editor extension, follow the links on the official quickstart to the relevant pages.
After signing in, how do I start working on a local project?
Follow the official desktop workflow:
From the download entry point on the quickstart page, choose the app for your operating system, install it, and open it.
Sign in with your own ChatGPT account.
From the ChatGPT dropdown menu, select Codex to enter the coding workspace.
Open the project folder you want to work on, then describe the task.
When working on a local project, first confirm that you have opened the target folder, then ask Codex to answer based on the files inside it and to list the paths it cites. You can also add relevant files or context as the task requires; you do not need to make the entire project the scope of your first task.
I want to work on tasks on the web — how do I prepare a cloud environment?
In a new task, select Work in > Cloud, open Select environment, then choose Create environment.
Codex will inspect the repository and help prepare and test the environment setup. Once you confirm the setup is as expected, you publish the environment; after publishing, you can start and continue cloud tasks on the web, on mobile, or in the desktop app.
It is advisable to first check the target repository and the environment check results. If problems arise during preparation, resolve the environment setup first, then submit the coding task.
How should I write the first task?
The official guidance is to state the goal and add the files or context needed. In practice, you can structure your request into three parts: goal, scope, and deliverable.
Suppose you have just taken over an existing project. You could start like this:
Read the project documentation and related configuration, and explain how the project starts. List the startup entry point, the file paths this is based on, and any prerequisites I need to confirm. For now, only read — do not modify files; clearly mark anything you cannot confirm.
The acceptance criterion for this task is a startup explanation backed by files. If the answer is vague, keep asking for the relevant paths or configuration details, and only arrange modifications once the evidence is in place.
After receiving the answer, how do I judge whether the task is complete?
Open the files the answer cites and check whether the startup command, entry point, and prerequisites are consistent. If you find a contradiction, feed back the specific file and the point of contradiction, and ask it to re-check.
When you later need code changes, describe the behavior you want changed, the scope of modifications allowed, and the verification requirements, and ask it to distinguish between checks it has already run and parts not yet verified. That way you can judge whether the result meets the requirements and what additional verification is still needed.
Which entry point should I choose the first time I use Codex?
Choose by where you work: use the desktop app for local projects, the web cloud for remote tasks, Codex CLI if you are used to a terminal, and the IDE extension if you want to stay in your editor. Just pick one entry point and complete the task.
How do I start working on a local project in the desktop app?
Download the app for your operating system from the official quickstart page, sign in with your ChatGPT account, select Codex from the menu, open the target project folder, then describe the task.
How should I phrase the first task?
Write it in three parts — goal, scope, and deliverable — and state clearly whether it may only read or may also modify. For example, first have it read the project documentation and configuration, explain how the project starts, list the file paths it relies on, and mark anything it cannot confirm.
How do I judge whether Codex's answer is trustworthy?
Open the files it cites and check them. If you find a contradiction, feed back the specific file and the point of contradiction and have it re-check; when you later request code changes, ask it to distinguish between checks it has performed and parts not yet verified.
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.
There is no fixed completion time for a top-up: account status, official risk control, queue conditions, and payment confirmation together determine how fast it goes. We do not make a fixed promise; the status on the order page is authoritative. This article breaks down the four factors and explains when to keep waiting and when to contact support.
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.
According to two official Google documents checked on 2026-11-18, the Gemini pages list no student discount or student plan. What can be confirmed about family arrangements is Google One family sharing: storage, benefits and support shared with up to 5 family members, excluding the 30 GB Lite tier, and whether AI benefits extend to the family group must be confirmed item by item. This article answers whether there is any basis for a student price, what family sharing actually shares, why pricing can only be seen at checkout, and how region and age restrictions apply, with a tier comparison table, a five-step check order and alternative routes.