--- id: chatgpt-connecting-to-your-tools lang: en track: chatgpt title: "Connecting ChatGPT to your tools" seoTitle: "ChatGPT apps: connect Drive, Slack and email" description: "How ChatGPT apps connect to the tools you already use, what an app can see and do, how to set its permissions, and how to connect it safely at your work." part: working-smart partTitle: "Working smart" partOrder: 4 order: 5 level: Intermediate durationMinutes: 6 outcome: "Connect ChatGPT to the apps you use at work, choose what each one may do, and use them safely." summary: "Apps connect ChatGPT to your email, files, calendar, and team tools, so it works with live information instead of copy-paste. Connect only what you need, set what each app may do, and check before it acts." draft: false updated: "2026-10-14" furtherReading: - title: "Connected apps in ChatGPT" url: "https://help.openai.com/en/articles/11487775-apps-in-chatgpt" note: "Connecting apps, what they can access, and the permission options." - title: "Admin controls, security, and compliance for plugins and apps" url: "https://help.openai.com/en/articles/11509118-admin-controls-security-and-compliance-in-apps-enterprise-edu-and-business" note: "What your workspace admin decides, including team-wide connections." - title: "Developer mode and MCP apps in ChatGPT" url: "https://help.openai.com/en/articles/12584461-developer-mode-apps-and-full-mcp-connectors-in-chatgpt-beta" note: "Custom MCP apps, which plans can use them, and the risks." - title: "Plugins in ChatGPT" url: "https://help.openai.com/en/articles/20001256-plugins-in-chatgpt" note: "How apps ship inside plugins, back from lesson 4.2." keywords: - ChatGPT apps - ChatGPT connectors - connect ChatGPT to Google Drive - ChatGPT Slack - ChatGPT app permissions - MCP ChatGPT quiz: intro: "Five quick questions, and Part 4 is done." passScore: 5 questions: - q: "What does an app do in ChatGPT?" options: - "It makes ChatGPT faster at certain tasks" - "It connects ChatGPT to a tool, to read or act there" - "It installs a ChatGPT button inside another program you use" - "It adds a new skill to your workspace" answer: 1 explain: "An app is a connection to a service you already use. ChatGPT can search and read there, and, with the right permission, act there too, instead of you copying things in and out." - q: "You connect your company's file storage. Can ChatGPT now open files you yourself can't?" options: - "No; it only reaches what your account can access" - "Yes, once you set it to Allow all actions" - "Yes, read-only, so it can search across the whole company" - "Only for files shared with the whole company" answer: 0 explain: "Apps sign in as you and respect the access you already have. App permissions decide what ChatGPT may do with that access; they never grant new access." - q: "Which permission setting is the most careful choice for an app that can send email?" options: - "Allow all actions" - "Allow low-risk actions" - "Allow read actions" - "Always ask" answer: 3 explain: "Always ask means ChatGPT checks with you before it acts in that app. Loosen it only for apps and actions where a mistake is cheap." - q: "Your admin has switched off an app your team wants. What's the right move?" options: - "Connect it through your personal account instead" - "Build a custom app in developer mode" - "Ask the admin why, and request it properly" - "Copy the data in by hand from now on" answer: 2 explain: "Admins decide which apps the workspace may use for good reasons: data protection, contracts, security. Ask and request; don't route around it." - q: "A colleague wants to connect a custom app through developer mode. What should they know?" options: - "It's riskier: apps need vetting, and admins turn it on" - "It's safe, because OpenAI reviews every custom app before use" - "It works on every plan, on web and mobile" - "It's read-only, so it can't change anything" answer: 0 explain: "Developer mode is for technical users connecting their own MCP apps. OpenAI flags the risks, write actions may need confirmation, and on Business only admins and owners can turn it on." pass: badge: "Part 4 complete" title: "Part 4 done. ChatGPT works with your real tools now." body: "Full marks. You can connect apps, set what they may do, and keep them safe. Part 5 is next: Codex, building things, and putting ChatGPT on a schedule." retry: "Check the marked answers and give it another go. You've got this." --- > **Level:** Intermediate ยท **Reading time:** ~6 min > > **What you'll be able to do:** connect ChatGPT to the apps you use at work, choose what each one may do, and use them safely. Up to now, ChatGPT has known what you gave it: a message, an upload, a project, a folder on your desktop. Your actual work lives elsewhere. In your inbox, your calendar, your shared drive, your team chat, your CRM. And so far, the bridge between them has been **you, copying and pasting.** **Apps** remove that step. Connect ChatGPT to the tools you already use and it can look things up, read the latest version, and, if you allow it, take action there. This is the lesson that turns ChatGPT from a smart assistant next to your work into one that works **inside** it. ## What an app is An **app** is a connection between ChatGPT and an outside service: Google Drive, SharePoint, Outlook, Gmail, Slack, Notion, a CRM, and many more. You'll find them under **Apps** in the sidebar or settings, and inside many **plugins** ([lesson 4.2](/learn/chatgpt/working-smart/skills-and-plugins)), which bundle apps with skills. Once an app is connected, ChatGPT can use it in three ways: - **Search and read.** "Find the latest version of the Acme proposal in Drive and summarise what changed." - **Bring live information into a chat.** This week's calendar, the thread from yesterday, the open deals. - **Act, when you allow it.** Draft and send an email, create a document, post a message, update a record. You can let ChatGPT decide when an app helps, or call one explicitly with an **@mention** or from the **+** menu. In deep research and in **Work** ([lesson 4.4](/learn/chatgpt/working-smart/chatgpt-work-on-your-files)), apps become sources and tools for the whole task.
ChatGPT, connected ChatGPT in the middle, connected to six apps: mail, calendar, files, team chat, CRM and a notes app. Solid lines are read: search and look things up. Dashed lines are act: send, create or update, which you can require to be approved first. ChatGPT, connected Each app signs in as you. It reads what you can read, and acts only as far as you allow. Mail Calendar Files Team chat CRM Notes ChatGPT read: search, look up act: send, create, update (you decide)
## Connecting one Connecting takes a minute: 1. Open **Apps**, pick the one you need, and choose **Connect**. 2. **Sign in** to that service with your own work account and approve the access it asks for. 3. **Set its permissions** (next section). 4. **Try it** in a chat: "Using Drive, find..." Two things to know on **Business**. Your **admin decides which apps** your workspace may use at all; if one is missing, that's a choice, not a glitch. And since late September, admins can set up some apps **team-wide**, so a shared tool works for everyone without each person connecting it. **Which plans:** apps exist on every plan, but which apps and actions you get depends on your plan, region, and workspace. On Business many apps are on by default, and your admin can change that. ## What an app can see This is the most important rule in the lesson: **an app works as you.** It signs in with your account and reaches only what that account can already reach. It doesn't unlock folders you can't open or channels you aren't in. **App permissions don't grant new access.** They only decide what ChatGPT may do *with* the access you already have. Two more details worth knowing. An app can see the **context of the chat** it's used in, and your **memories** where relevant; ChatGPT can also save useful things it read in an app to memory. So the habits from [lesson 1.4](/learn/foundations/ai-at-work-safety-and-privacy) apply to what you put in that chat. On Business, **data from apps isn't used to train OpenAI's models** by default. On personal plans it can be, if "Improve the model for everyone" is on. ## Choosing what each app may do For each connected app you choose how much ChatGPT may do without checking with you. There are four settings: - **Always ask.** ChatGPT asks before every action in the app. The safest choice. - **Allow read actions.** It can search and read freely, but asks before changing anything. - **Allow low-risk actions.** Small actions, like creating a draft, go ahead; bigger ones still need you. - **Allow all actions.** It acts without asking. Only offered for some apps and accounts; reserve it for apps where a mistake costs almost nothing. **Match the setting to the stakes.** Reading a public knowledge base: allow read actions. Email, money, customer records, anything sent in your name: always ask. You can change the setting any time.
How much may each app do? Four permission settings as steps, from safest at the bottom to fastest at the top: Always ask, Allow read actions, Allow low-risk actions, and Allow all actions, which is only offered for some apps and accounts. How much may each app do? Four settings per app. Start careful; loosen only where a mistake is cheap. Always ask Asks before every action. Allow read actions Reads freely, asks before changes. Allow low-risk Small actions go ahead. Allow all actions Acts without asking. Some apps only. SAFER Email, money, customers: always ask.
## Using apps well A few habits make apps work better and stay safer: - **Connect what you use, not everything.** Each app's results take room in the context window ([lesson 4.1](/learn/chatgpt/working-smart/context-and-memory)), and each connection is one more way in. - **Name the source.** "In Slack, #sales-team, last week" gets you a better answer than "check what people said." - **Check what it read.** ChatGPT shows which app and which file or message it used. Click through when it matters. - **Read before you approve.** When ChatGPT asks to send, post, or change something, check the content and the recipient. You're responsible for what goes out. **A worked example.** On Monday morning: "Using Outlook and my calendar, list the meetings I have this week, and for each one find the latest related email thread and write two lines on what I need to prepare." Three tools, one answer, no copy-paste. If you ask it to email the summary to your manager, it asks first. ## For the technical: custom apps Most people never need this section. Under the hood, many apps use an open standard called **MCP** (Model Context Protocol), the same one Claude and others use. With **developer mode**, technical users can connect their own MCP app, for example to an in-house system. Know the limits before you try. It's a **beta**, on the **web** only. Full MCP, including write actions, is for Business, Enterprise, and Edu; on **Business, only admins and owners** can turn it on. Pro can build apps with OpenAI's Apps SDK but doesn't get full MCP. OpenAI warns plainly that untrusted apps can expose you to **prompt injection**: outside content trying to give ChatGPT instructions. Write actions may need your confirmation, the riskiest ones can be blocked, and **your organisation is responsible for vetting** the apps it connects. If you're not the one who built the app, check with whoever did, and with IT. ## That's Part 4 You can now work with ChatGPT like a power user: - Keep the **context window** lean and **memory** accurate (4.1). - Package repeatable jobs as **skills**, shipped in **plugins** (4.2). - Give ongoing work a home in a **project** (4.3). - Hand whole tasks to **Work**, on your own files (4.4). - Connect ChatGPT to your **tools**, with the right permissions (4.5). **Part 5** takes it further: **Codex** for building and code, putting ChatGPT on a **schedule** so work happens without you starting it, and ready-made **playbooks** for common jobs. ## Try it Pick **one** tool you copy from most: your email, your shared drive, or your team chat. Connect it, and set its permission to **Always ask** to start. Then ask a real question that needs it: **"Using [app], find what we last agreed with [client or colleague] about [topic], and summarise it in three lines with links."** Click through to the source to check it. Once you trust the pattern, decide whether that app deserves a looser setting, or not. *(General exercise. Role and industry versions come once accounts are in.)* ## Key terms [App](/glossary#chatgpt-app), [Plugin](/glossary#chatgpt-plugin), [MCP](/glossary#mcp), [Prompt injection](/glossary#prompt-injection), [ChatGPT Work](/glossary#chatgpt-work)