# ChatGPT Guides

> Source: https://aiwiki.ai/wiki/chatgpt_guides
> Updated: 2026-05-09
> Categories: ChatGPT, OpenAI
> From AI Wiki (https://aiwiki.ai), a free encyclopedia of artificial intelligence. Quote with attribution.

*See also: [Guides](/wiki/guides), [ChatGPT](/wiki/chatgpt) and [Prompt engineering](/wiki/prompt_engineering)*

**ChatGPT Guides** is the AI Wiki gateway to how-to material for [ChatGPT](/wiki/chatgpt), the conversational assistant built by [OpenAI](/wiki/openai). The article links every walkthrough, tutorial, and reference page that explains how to sign up, write prompts, build [Custom GPTs](/wiki/custom_gpts), use voice and vision, work with files, run code, browse the web, and connect [ChatGPT](/wiki/chatgpt) to other tools. It also collects context on pricing tiers, privacy controls, and common pitfalls. ChatGPT was first released on 30 November 2022 and has since grown into a multimodal product that runs on the web, on iOS and Android phones, on macOS and Windows desktop apps, and through the [OpenAI API](/wiki/openai_api). The guides on this hub cover the consumer product (ChatGPT) rather than direct API integration, which has its own gateway at [OpenAI API](/wiki/openai_api).

## what this hub covers

The pages indexed here treat ChatGPT as a working tool. Guidance focuses on tasks an end user can actually perform: opening an account, choosing a plan, writing a prompt that returns useful output, attaching files, calling a [Custom GPT](/wiki/custom_gpts), turning on memory, switching to voice, and so on. Theory pages such as [Large Language Model](/wiki/large_language_model), [Transformers](/wiki/transformers), and [Reinforcement Learning from Human Feedback (RLHF)](/wiki/rlhf) are linked from this hub but live in their own articles.

## getting started

### sign-up

A new user can create a free ChatGPT account at chatgpt.com using an email address, a Google account, an Apple ID, or a Microsoft account. OpenAI requires a phone number to verify the account on first sign-in, which is used to deter abuse. After verification the user lands on the chat interface and can start a conversation immediately. The account also unlocks access to the iOS app, the Android app, and the desktop apps for macOS and Windows, all of which sync conversation history across devices when signed in.

### plans and pricing

OpenAI offers a tiered set of consumer and business plans. Pricing and quotas have changed several times since 2023, so the table below lists each plan and the model access OpenAI has publicly described.

| Plan | Monthly price (USD) | Who it is for | Notable features |
|---|---|---|---|
| Free | $0 | New users and casual use | Access to a default model with limited usage, basic data analysis, image uploads, voice chat, and access to [Custom GPTs](/wiki/custom_gpts) created by others |
| Plus | $20 | Individuals who use ChatGPT often | Higher message caps, faster response times during peak hours, advanced voice mode, image generation, deep research, and access to higher-end models |
| Pro | $200 | Power users and researchers | Near-unlimited access to the most capable models, including extended reasoning models in the [OpenAI o-series](/wiki/openai_o-series), longer context, and priority access to new features |
| Team | $25 per seat (annual) or $30 per seat (monthly) | Small teams and businesses | Higher message caps than Plus, a shared workspace, admin console, and a commitment that team data is not used to train OpenAI models by default |
| Enterprise | Custom | Large organizations | Single sign-on, SCIM provisioning, audit logs, longer context windows, advanced data privacy, and a custom data retention policy |
| Edu | Custom | Universities | Enterprise-grade features for accredited institutions, with admin tools tailored to campus rollouts |
| API | Pay as you go | Developers | Token-priced access to models through the [OpenAI API](/wiki/openai_api), the [OpenAI Responses API](/wiki/openai_responses_api), and the [OpenAI Realtime API](/wiki/openai_realtime_api) |

Message caps and model availability shift over time as OpenAI rolls out new models. The official source of truth is the OpenAI pricing page and the in-product model picker.

### apps and clients

ChatGPT runs in any modern browser at chatgpt.com. OpenAI also publishes:

* iPhone and iPad app on the App Store, with widgets, Siri shortcuts, and integration with Apple Intelligence on supported devices.
* Android app on Google Play.
* Native macOS app with a system-wide keyboard shortcut to open a focused chat window over any other application.
* Native Windows app with a similar shortcut.

All clients share the same account, the same conversation history, and the same memory store. Users can start a conversation on the phone and finish it on the desktop.

## prompt engineering

The quality of any ChatGPT answer depends on the [prompt](/wiki/prompt). The hub links to long-form material on writing better prompts:

* [Prompt Engineering](/wiki/prompt_engineering) is the full reference article on the discipline.
* [Prompt engineering for text generation](/wiki/prompt_engineering_for_text_generation) walks through writing assistants, summarization, and structured output.
* [Prompt engineering for image generation](/wiki/prompt_engineering_for_image_generation) covers prompts for image models inside and outside ChatGPT.
* [26 Principles of Good Prompts](/wiki/26_principles_of_good_prompts) is a checklist drawn from the academic paper of the same name.
* [Chain-of-Thought Prompting](/wiki/chain_of_thought) explains the technique of asking the model to reason step by step.
* [ReAct (prompting)](/wiki/react_prompting) covers the reasoning-and-acting pattern used in agent frameworks.
* [Meta Prompting](/wiki/meta_prompting) explains how to use a model to write its own prompts.
* [Tree of Thoughts](/wiki/tree_of_thoughts) covers a search-style prompt strategy.
* [System prompt](/wiki/system_prompt) explains the role-priming text that sits above the conversation.

A few practical habits cover most everyday prompts. State the role you want the model to take. State the task in a single clear sentence. Provide context, examples, and constraints. Ask for the format of the answer (a bulleted list, a JSON object, a table). For complex tasks, ask the model to think step by step or to draft an outline before writing the final answer. When an answer is wrong, push back with a follow-up message instead of starting a new chat: ChatGPT can revise inside the same context.

## custom gpts

A [Custom GPT](/wiki/custom_gpts) is a packaged version of ChatGPT with a name, an icon, a system prompt, optional knowledge files, optional tools (web browsing, code interpreter, image generation), and optional API actions. OpenAI launched the feature in November 2023 at DevDay and opened a public catalog called the [GPT Store](/wiki/gpt_store) in January 2024.

### building a custom gpt

A Plus, Pro, Team, or Enterprise subscriber can build a Custom GPT in a guided UI:

1. Open the GPT builder from the sidebar.
2. Describe the GPT in natural language. The builder writes a draft system prompt, name, description, and conversation starters.
3. Refine the system prompt with explicit rules, tone instructions, and formatting requirements.
4. Upload reference files. ChatGPT will retrieve from these documents at runtime through retrieval-augmented generation, an approach covered in detail at [Retrieval-augmented generation](/wiki/retrieval_augmented_generation).
5. Toggle which built-in tools the GPT can use.
6. Add custom actions. These are HTTP endpoints described with an OpenAPI schema, which lets the GPT call any web API on the user's behalf.
7. Choose the visibility: private, link-only, or published to the [GPT Store](/wiki/gpt_store).

At the time of writing, the [GPT Store](/wiki/gpt_store) hosts hundreds of thousands of Custom GPTs across categories such as writing, productivity, research, programming, lifestyle, and education. Notable examples include [GPT-4 (Custom GPT)](/wiki/gpt-4_custom_gpt), [ChatGPT Classic](/wiki/chatgpt_classic), and many third-party tools for specific workflows.

## plugins (legacy)

Before Custom GPTs, OpenAI shipped a plugin system that let third parties expose tools to ChatGPT through manifests and OpenAPI specs. The flagship example was the [ChatGPT Retrieval Plugin](/wiki/chatgpt_retrieval_plugin), which let a user point ChatGPT at a private vector store of documents.

OpenAI deprecated the plugin store on 9 April 2024 and removed plugin features from ChatGPT during 2024. Existing functionality moved into Custom GPTs (for tool-style integrations) and Connectors (for managed enterprise data sources). The plugin pages on this wiki are kept for historical reference.

## voice, vision, and multimodal use

ChatGPT is multimodal: it accepts and produces text, images, audio, and (in some clients) live video.

* **Voice mode** lets the user speak to ChatGPT and hear a spoken reply. The original voice mode launched in September 2023 with text-to-speech voices designed by professional voice actors. **Advanced Voice Mode**, released in 2024, runs on a speech-native model and supports interruptions, emotion, and lower latency. The technology is closely related to the [OpenAI Realtime API](/wiki/openai_realtime_api), which exposes the same speech-to-speech capability to developers.
* **Vision** lets the user attach a photo, screenshot, or PDF and ask questions about it. ChatGPT can read text in images, describe scenes, identify objects, and analyze charts.
* **Image generation** is built into ChatGPT through OpenAI's image models. The lineage runs from [DALL-E](/wiki/dall-e) through later in-product image models. A user can ask the chat to generate, edit, and iterate on images directly inside the conversation.
* **Video** is supported through file uploads of short clips and, on some plans, through a live video session in the mobile app.

Vision and voice work together with the rest of the system. A user can speak a question, attach a photo, and receive a written or spoken answer that references both inputs.

## memory and personalization

ChatGPT has a memory feature that stores small pieces of information across conversations. When the user mentions a fact about themselves (their name, their job, an ongoing project, a writing style), ChatGPT can save it and use it later without being told again. Memory can be inspected, edited, and cleared from Settings under Personalization. A temporary chat starts with no memory access and is not saved.

Custom Instructions are a related feature. The user fills in two text boxes that describe themselves and how they want ChatGPT to respond. Those instructions are added to every new chat as a hidden system message. Users often combine Custom Instructions with memory to lock in tone, formatting, and recurring constraints.

## code interpreter and advanced data analysis

ChatGPT can execute Python in a sandboxed virtual machine. The feature was announced in March 2023 as Code Interpreter, renamed Advanced Data Analysis later in 2023, and rolled into the default toolset of capable models in 2024. Inside the sandbox the model can:

* read CSV, Excel, JSON, PDF, image, and audio files that the user uploads.
* run pandas, NumPy, scikit-learn, matplotlib, and other common libraries that ship with the environment.
* draw charts and return them as images.
* compress, convert, edit, and merge files.
* run small simulations and statistical tests.

For straightforward data work, this is often faster than writing a notebook from scratch. The [OpenAI Codex](/wiki/openai_codex) line and the [Codex (OpenAI)](/wiki/codex) coding agent share lineage with this feature; the related [Programming with ChatGPT](/wiki/programming_with_chatgpt) guide is linked from this hub.

## chatgpt search

ChatGPT Search lets the assistant fetch live information from the web. The feature was launched as SearchGPT in July 2024, opened to ChatGPT Plus and Team in October 2024, and rolled out to free users during 2025. Search returns linked citations alongside the model's answer, so a user can click through to the source. Typical use cases include checking news, researching products, finding recent papers, and pulling specific facts that postdate the model's training cutoff. ChatGPT chooses when to search automatically, but the user can also force a search with a button or a slash command.

## operator and agent mode

[OpenAI Operator](/wiki/openai_operator) is a research preview agent that controls a remote web browser to perform tasks on the user's behalf. Operator launched as a Pro-tier feature on 23 January 2025 and extended ChatGPT's reach from a chat box to a system that can fill in forms, click buttons, and complete checkouts. Through 2025 OpenAI folded Operator into a broader Agent Mode in ChatGPT, which combines browsing, code execution, and tool use to plan and complete multi-step jobs.

Agent Mode and Operator share infrastructure with the [OpenAI Agents SDK](/wiki/openai_agents_sdk), which gives developers a programmatic way to build similar agents on top of the [OpenAI API](/wiki/openai_api).

## privacy and data controls

OpenAI documents data handling in its Privacy Policy and in the in-product Data Controls page. Key points for individual users:

* By default, conversations on the consumer Free, Plus, and Pro plans may be used to improve OpenAI models. The user can disable this in Settings under Data Controls. When training is off, conversations are still saved to history but are not used for model training.
* Temporary Chat is a chat mode that does not save to history, does not appear in memory, and is not used for training. Conversations may still be retained for a short period to monitor for abuse.
* Team and Enterprise data is not used for training by default.
* The user can export the full account data archive (conversations, memory, settings) from Settings.
* The user can delete individual chats, the entire conversation history, or the whole account.

For research on adversarial attacks against this kind of system, see [Prompt injection](/wiki/prompt_injection) and [How to Steal ChatGPT-4, GPT-4 and other Proprietary LLMs](/wiki/how_to_steal_chatgpt-4_gpt-4_and_other_proprietary_llms).

## models inside chatgpt

The model picker shows different model names depending on the plan. The list below sketches the main families that have appeared inside the chat product. Detailed history lives in the linked articles.

| Family | Notable models | What they are good at |
|---|---|---|
| GPT-3.5 | gpt-3.5-turbo | The default in the original Free tier; cheap and fast. |
| [GPT-4](/wiki/gpt-4) | gpt-4, gpt-4-turbo | The first model in ChatGPT with strong reasoning and long context. |
| GPT-4o | gpt-4o, gpt-4o mini | Multimodal model (text, vision, audio). Default for Free and Plus through 2024 and 2025. |
| [GPT-5](/wiki/gpt-5) | gpt-5 family | Successor flagship released in 2025, used for general chat on paid plans. |
| o-series | [o1](/wiki/o1), [o3](/wiki/o3), [o4-mini](/wiki/o4_mini) | Reasoning models that think before they answer; covered at [OpenAI o-series](/wiki/openai_o-series). |

Reasoning models from the [OpenAI o-series](/wiki/openai_o-series) tend to take longer to answer and are better at math, code, and multi-step problems. Standard chat models tend to be faster and more conversational. Most users mix the two depending on the task.

## integrations

ChatGPT connects to other software in several ways:

* **File uploads** accept Office documents, PDFs, code, images, audio, and short video clips.
* **Connectors** on Team and Enterprise plans link ChatGPT to Google Drive, OneDrive, SharePoint, GitHub, and other corporate sources, so the assistant can search across enterprise data with the user's own permissions.
* **Apple Intelligence** integration on iOS and macOS routes Siri queries and writing tools to ChatGPT when the user opts in.
* **Custom Actions** in Custom GPTs let a single GPT call any HTTP API.
* **Direct integrations** with note apps, IDEs, and browsers exist through third-party extensions.

For server-to-server integration without the chat UI, developers usually go straight to the [OpenAI API](/wiki/openai_api), [OpenAI Responses API](/wiki/openai_responses_api), or [Azure OpenAI Service](/wiki/azure_openai).

## common pitfalls

A short list of issues that come up in the day-to-day use of ChatGPT:

* **Hallucination.** ChatGPT can write a confident answer that is wrong. The fix is to ask for citations, to enable web search for time-sensitive questions, and to verify any fact that matters before acting on it.
* **Stale knowledge.** Each model has a training cutoff. Information about events after that date is missing or guessed unless the model uses search.
* **Context limits.** Long conversations or large file uploads eventually fall out of the context window. The model loses track of details from earlier in the chat. Starting a fresh conversation, or summarizing the prior context into a single prompt, often fixes the problem.
* **Tool confusion.** When a chat has many tools enabled, the model sometimes picks the wrong one. Telling the model which tool to use, or building a Custom GPT with a narrower toolset, helps.
* **Over-trust on math and code.** Even with Code Interpreter, the model can write a plausible script with a subtle bug. Run the code, read the output, and treat the assistant as a fast first draft.
* **Privacy slips.** Pasting confidential data into a personal account is risky. Team and Enterprise plans, or a Temporary Chat with training disabled, are safer for sensitive material.
* **Prompt injection.** A document or web page can carry hidden instructions that try to hijack the assistant. See [Prompt injection](/wiki/prompt_injection) for the threat model.

## related pages on aiwiki

* [ChatGPT](/wiki/chatgpt)
* [ChatGPT Uses](/wiki/chatgpt_uses)
* [Programming with ChatGPT](/wiki/programming_with_chatgpt)
* [Fine-tune ChatGPT with Perplexity, Burstiness, Professionalism, Randomness and Sentimentality Guide](/wiki/fine-tune_chatgpt_with_perplexity_burstiness_professionalism_randomness_and_sentimentality_guide)
* [GPT Store](/wiki/gpt_store)
* [Custom GPTs](/wiki/custom_gpts)
* [GPT-4 (Custom GPT)](/wiki/gpt-4_custom_gpt)
* [ChatGPT Classic](/wiki/chatgpt_classic)
* [OpenAI Pulse](/wiki/openai_pulse)
* [OpenAI Operator](/wiki/openai_operator)
* [OpenAI Codex](/wiki/openai_codex)
* [OpenAI o-series](/wiki/openai_o-series)
* [Sora](/wiki/sora)
* [DALL-E](/wiki/dall-e)
* [Sam Altman](/wiki/sam_altman)
* [Guides](/wiki/guides)

## references

1. OpenAI. "Introducing ChatGPT." OpenAI Blog, 30 November 2022.
2. OpenAI. "ChatGPT can now see, hear, and speak." OpenAI Blog, 25 September 2023.
3. OpenAI. "Introducing GPTs." OpenAI Blog, 6 November 2023.
4. OpenAI. "Introducing the GPT Store." OpenAI Blog, 10 January 2024.
5. OpenAI. "Hello GPT-4o." OpenAI Blog, 13 May 2024.
6. OpenAI. "Introducing SearchGPT." OpenAI Blog, 25 July 2024.
7. OpenAI. "ChatGPT search is now available." OpenAI Blog, 31 October 2024.
8. OpenAI. "Introducing Operator." OpenAI Blog, 23 January 2025.
9. OpenAI Help Center. "What is ChatGPT?"
10. OpenAI Help Center. "Memory FAQ."
11. OpenAI Help Center. "Data Controls FAQ."
12. OpenAI Help Center. "How your data is used to improve model performance."
13. OpenAI Help Center. "Voice mode FAQ."
14. OpenAI Help Center. "Custom GPTs FAQ."
15. OpenAI. "OpenAI Pricing." pricing page, accessed 9 May 2026.
16. Wikipedia contributors. "ChatGPT." Wikipedia, accessed 9 May 2026.
17. Wikipedia contributors. "OpenAI." Wikipedia, accessed 9 May 2026.
18. Bsharat, Sondos M., Aidar Myrzakhan, and Zhiqiang Shen. "Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4." arXiv:2312.16171, 2023. (Source for [26 Principles of Good Prompts](/wiki/26_principles_of_good_prompts).)
19. Wei, Jason, et al. "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models." arXiv:2201.11903, 2022. (Background for [Chain-of-Thought Prompting](/wiki/chain_of_thought).)