The Complete Gemini Guide

Gemini is Google's AI, and in 2026 it is a lot more than the chat box at gemini.google.com. It is the assistant on Android phones, a native app on Mac and Windows, a side panel in Chrome, a helper inside Gmail and Docs, an agent mode called Tasks that keeps working after you close your laptop, and the engine behind Google's image, video and music generators. If you already use Google's apps, connecting the ones you need can make Gemini more useful for your everyday work. Access depends on your account, settings and region.

This guide walks the whole product the way it looks today. Which model to pick, which plan is worth paying for, where every feature lives, and the settings that decide what Google keeps about you.

Getting Started

You need a personal Google account. Sign in at gemini.google.com and you are chatting. Once you are set up, my Gemini secret codes list gives you 100 shortcuts to paste straight in, and Google's free AI tools covers the rest of the Google lineup. Start with the features available in your account. Plans, ages, regions and work or school policies affect access. Where you use it matters a little more than it used to, because the apps are not all identical:

• Web (gemini.google.com): the full product. Chat, Deep Research, Canvas, skills, Notebooks, image and video creation, Tasks, settings.
• Android: Use Gemini as your digital assistant on supported Android devices. Activation and available app actions depend on your phone and settings.
• iPhone: the Gemini app from the App Store, plus Gemini inside Chrome for iOS.
• Mac and Windows: native desktop apps at gemini.google/desktop. On Mac, Option + Space opens a mini window from anywhere. On Windows it is Alt + Space. Feature availability differs between desktop apps and the web. Tasks currently work on the web, mobile and the Mac app; do not assume Windows has every Mac feature.
• Chrome: a Gemini button in the top right of the browser summarizes pages, compares tabs, and on paid plans can browse and fill forms for you.
• Gmail and Docs: Gemini is built into Gmail for free (summaries, Help me write, suggested replies), and into Docs, Sheets, Slides, Drive and Meet on the paid plans.

The Interface

The app was redesigned in 2026 and it is cleaner than it used to be. Use the left menu to find chats, saved creative work, skills and Notebooks. Click Customize in the left menu to set your response style, add skills and connect apps (more than 40 of them, like Instacart, OpenTable and Adobe). Next to the prompt box there is a Chat / Task toggle: Chat for normal questions, Task for jobs you want Gemini to run in the background.

Use the prompt box for your request and its attachment control for files. Choose a tool such as Deep Research or Canvas when that is the job you want to do. Review the model and thinking options shown in your account before sending a difficult task.

For uploads, start with one file and name the pages, columns or sections you want analyzed. Limits differ by file type, length, plan and platform. If a file is rejected, split it into relevant sections or use a smaller export. Ask Gemini to confirm what it could read before relying on its summary.

The Models, Explained

The picker shows four models: Flash-Lite, Flash, Pro and Argon. Version numbers change, so use the model names in your own picker as the current reference.

• Flash-Lite: quick, simple work and the fallback when you reach your limits.
• Flash: a useful everyday starting point for writing, planning and questions.
• Pro: harder analysis, coding and problems that need more reasoning.
• Argon: Google's top model (Gemini 4 Argon), for the most complex work. Pro and Ultra plans only.

Separately, you pick a thinking level: Low (the default), Medium or High. Higher levels give a problem more thought and use more of your allowance. Without a plan you get Auto or Flash-Lite. Google AI Plus adds Flash and Pro. Pro and Ultra get all four.

Pricing: What You Actually Get

Compare the current offer for your country at Google AI plans. These are the listed U.S. monthly base prices at verification, before temporary promotions. Your checkout is the final price.

Paid features still have account and region requirements. Tasks, for example, need Pro or Ultra, a personal account and a supported country. Check access in your own account before buying a plan for one feature.

Use the free plan for a week before choosing. Write down which limits you actually hit and which feature you would pay for. Extra storage can matter, but it is not a reason to buy an AI tier you will not use.

Deep Research

Deep Research is Gemini's research agent. You give it a question, it plans a search, reads dozens of sources, and comes back with a cited report, with links you can check. Free access is limited and can be affected by demand.

Choose Deep Research from the prompt tools, give it a specific question and review the research plan before starting. Add relevant files or enable the connected sources you want it to use. Open the finished report, inspect important citations and ask follow-up questions before using its conclusions. Curious how it compares? Here's ChatGPT's version.

Research [TOPIC] for me. I want to understand the current state of it, who the key players are, what changed in the last 12 months, where the experts disagree, and what a smart person would do about it. Cite your sources, flag anything that is opinion rather than fact, and finish with the three things you are least sure about.

Skills (Formerly Gems)

A skill is a set of standing instructions Gemini applies when you need them. Make one for the tasks you repeat: a writing assistant that knows your voice, a study coach for one class, a meal planner that knows your allergies. Skills are replacing Gems, and they're rolling out to everyone through mid-November.

Where it lives: open Customize in the left menu to add a skill, or ask Gemini to turn something from a chat into a skill. To use one, type / followed by the skill name in any chat. You can stack more than one in the same prompt. Gemini can also run a skill on its own when your prompt matches.

Already have Gems? They still work. On November 17, 2026 they move into Settings, and later they get turned into draft skills you review and switch on.

You are my editor. Every time I paste a draft, do three things in this order: (1) tell me the one thing that is most unclear to a first-time reader, (2) cut it by 20 percent without losing any point, (3) return the edited version with your changes in bold. Keep my voice. Never add an intro or a summary. Ask me one question at the end if something is genuinely ambiguous.

Canvas

Canvas is a workspace next to the chat for documents, code and pages. Instead of regenerating a whole answer, you edit it in place. Highlight a paragraph and ask for a rewrite, change the tone of one section, or build a working web page and preview it.

Where it lives: choose Canvas from the prompt tools, describe the document or app, and refine the result in the workspace. Use the available sharing or export controls when you are ready. Check the actual exported file before sending it to someone.

Open this in Canvas. Write a one-page landing page for [PRODUCT] with a headline, three benefits, one short testimonial placeholder, and a single call to action. Then give me three alternative headlines below it and tell me which one you would test first and why.

Gemini Live

Live is the voice mode, and it now lives right inside your chat. Tap the Live icon to start talking, and you can switch between talking and typing in the same thread without losing your context. It is a real conversation: interrupt it, change the subject, think out loud.

The part that makes it different from every other voice assistant is that it can see. On your phone, tap the camera icon and point it at something, and it can tell you what it is, read the label, translate the sign, or walk you through fixing it. Turn on screen sharing and it can look at whatever is on your screen while you talk. Check the visible camera and screen-sharing indicators, and stop sharing when you are finished.

Images: Nano Banana

Nano Banana is the name of Gemini's image models. Nano Banana 2 is the everyday default, and paid plans can redo an image with Nano Banana Pro for higher quality. For better results, my Nano Banana prompt guide has the prompts.

Where it lives: open the sidebar and click Images, pick a template or type a prompt, or use Create image from the Tools menu. To edit something you made, open Library, click the image, click Chat underneath it, and describe the change. On a paid plan you can click More in the bottom right of any image and choose Redo with Pro. Downloads are 1K on the free tier and 2K on any paid plan.

Keep the generated image's provenance information. Inspect small text, hands, logos and product details before using a result.

Create a product photo of [ITEM] on a plain warm-white background, soft studio lighting from the top left, shallow depth of field, shot on a 50mm lens, no text, no logos, photorealistic. Then show me the same shot from a 45 degree angle.

Video: Gemini Omni

Omni is Gemini's video model. It makes 10-second clips from text, an image, or another video, and you can extend a scene in 10-second steps up to 40 seconds, set the first and last frame, draft at low resolution, and upscale to 4K. Video needs a paid plan (Plus, Pro or Ultra) and you have to be 18 or over.

Where it lives: open the sidebar and click Create video. Choose the aspect ratio, upload up to one video and five reference images if you want, and describe the shot. It takes a few minutes and you cannot use that chat while it works. Edits are conversational: ask it to remove an object, change the camera angle, or swap the scene, and it returns a new version.

For bigger video projects, Flow at flow.google.com is Google's full video studio, and it comes with the paid plans with its own monthly credits.

Music

Gemini can write songs now. Choose Create music from the Tools menu, describe the genre and mood, pick vocal or instrumental and short or long, and it produces a finished track. Availability and limits depend on your account and location.

Notebooks and Gemini Notebook

There are two notebook things and they sync with each other, which confuses everyone at first.

Notebooks inside the Gemini app live in the sidebar. Click New notebook, drop in chats, files and instructions, and every conversation you start inside it has all of that as context. This is how you keep a project or a class together.

Gemini Notebook is the standalone product at notebook.google (it used to be called NotebookLM, and the old notebooklm.google address forwards there). Upload your sources, and it answers only from them, makes study guides, flashcards and quizzes, and generates the famous podcast-style Audio Overviews and short Video Overviews. Sources, names and custom instructions can sync across the apps. Shared notebooks and chat context have additional restrictions, so check what is actually visible before relying on a sync.

Personal Intelligence and Memory

This is the feature that separates Gemini from everything else. Personal Intelligence lets Gemini use your Gmail, Calendar, Photos, Search history, YouTube, Contacts and Workspace files to answer you. "What was the name of the hotel we stayed at in Lisbon?" "Find the invoice from the plumber." "Pull the flight details from my confirmation email into my calendar."

Where it lives: turn it on in Settings (look for Personal Intelligence), and choose which apps it may use from Customize in the left menu. There is a Memory setting that lets it remember your past chats. Both need you to be 18 or over on a personal account, and availability varies by region and account. You can also switch Personal Intelligence off for a single chat from the Tools menu.

Google says it does not train on your Gmail or Photos through this feature, only on limited prompts and responses. Review which apps you have connected instead of assuming Gemini can see everything.

Look through my Gmail and Calendar for the last 30 days and give me a briefing: every commitment I made in an email that is not on my calendar yet, every unanswered message from a real person older than three days, and anything that looks like a bill or a deadline. Group it by urgency.

Daily Brief

If you turn on Personal Intelligence, Memory and your Workspace connection, Gemini builds you a morning briefing: Top of mind, FYI, and Looking ahead, assembled from your email, calendar and recent chats. It arrives as a notification and lives in the side panel, and you can ask for it in Live with "What's my daily brief?" U.S. only right now.

Connected Apps

Connected Apps are the services Gemini can act inside of. Google's own apps (Maps, YouTube, Photos, Home, Contacts, Messages) plus more than 40 third-party services like Instacart, OpenTable and Adobe. The current list in your account is the authority for what you can connect. In a chat, just name the app or type @ followed by the app name. Manage the list from Customize in the left menu. Most of the third-party ones are English-only in the U.S. for now.

@Google Maps find three coffee shops within a 10 minute walk of my next calendar event that are open before it starts, and @Google Calendar add a 20 minute buffer before the event so I have time to get there.

Schedules

Tell Gemini to do something on a schedule and it will. "Every Monday at 8am, give me a summary of the week's tech news." "On the first of the month, remind me to review my subscriptions." It confirms the schedule, and you manage everything from Scheduled in the sidebar, up to 10 active at a time. It needs Keep Activity turned on, and it is still rolling out to personal accounts.

Every weekday at 7:30am, send me a 5-bullet briefing: the top story in [MY INDUSTRY], anything on my calendar today that has no location or link attached, the weather where I am, one thing from my recent chats I said I would follow up on, and a single question to think about on my commute.

Tasks: The Agent (Formerly Spark)

Tasks is worth exploring if it is available in your paid account. It used to be called Spark. It is a personal agent that runs on Google's servers, so it keeps working after you close the laptop. Give it a goal, a list of steps, or a standing schedule, and it browses, books, fills forms, cleans your inbox, organizes Drive, and reports back.

Where it lives: on the web or the Mac app, click Task below the text box (or flip the Chat / Task toggle next to the prompt box), describe the goal, add files if you want, and send. Settings live under Settings, then Task settings on the web, and Gemini, then Settings, then Tasks on Mac. Requirements: Pro or Ultra, age 18+, a personal account, Keep Activity on and Personal Intelligence turned on. It is not available in the EEA, Nigeria, Switzerland or the UK, and it supports web, mobile and the Mac app.

Google's own rule is worth repeating: never type sign-in details or payment information into a task. If a site needs them, take over the browser and enter them on the page yourself. Set clear limits and supervise it. Some actions need confirmation, but do not assume every consequential action will automatically pause.

Task: Go through my Google Drive and find every file I have not opened in over a year. Group them by type and by the project they seem to belong to. Do not delete or move anything. Give me a table with your recommendation for each group (archive, keep, or review) and a one-line reason.

Gemini in Chrome

The Gemini button at the top right of Chrome opens a side panel that can read the page you are on. Ask it to summarize an article, compare the products in your open tabs, pull dates into your calendar, or explain a contract clause. It is free on desktop in the U.S., UK, Canada, India and a growing list of countries, and on Android and iPhone in the U.S.

On Pro and Ultra in the U.S. there is Auto Browse: Gemini clicks through sites for you, fills forms, and completes bookings and orders, pausing for your confirmation before anything sensitive.

Gemini in Gmail and Workspace

Gmail gets Gemini for free: AI Overviews that summarize a long thread, Help me write, and suggested replies. Asking questions across your whole inbox, Proofread, and the AI Inbox that sorts and triages for you need a paid plan (Plus and up). The Gemini side panel inside Docs, Sheets, Slides, Drive and Meet needs Pro or Ultra on a personal account.

In Gmail: find every email from the last two weeks where someone asked me a question I have not answered. List them with the person, the question in one line, and a suggested one-sentence reply for each.

Study Tools

Gemini has a real study kit built in. Ask for a quiz, flashcards or a practice test on any topic and it builds one. Guided learning in the Tools menu turns it into a tutor that teaches step by step instead of handing you the answer. Storybook writes and illustrates a ten-page picture book from a single prompt. The student hub at gemini.google.com/students lets you manage your classes and turn a syllabus into a study notebook.

Teach me [TOPIC] using guided learning. Start by asking me three questions to find out what I already know. Then teach the next concept in under 150 words, give me one practice problem, and do not move on until I get it right. Keep a running list of what I have mastered.

Privacy: The Settings That Matter

Review Gemini Apps Activity before connecting personal files or accounts.

Keep Activity: With it off, future chats are not used to train Google's AI models unless you submit feedback. Chats are still retained with your account for 72 hours, and human review can still occur for safety. Some connected features, including Tasks and Schedules, require activity to be on.

Auto-delete: The default is 18 months. You can choose a different retention period, including three months. Deleting Gemini activity does not delete data stored in other Google services.

Temporary chat: These chats do not appear in activity and are not used for model training. They still have a 72-hour retention window. Temporary chat is not the same as a zero-retention service.

Prompting Gemini Well

Gemini responds best to prompts that read like a brief to a capable colleague. Three habits that change the output more than anything else:

• Give it the job, the audience and the format. "Write a 200-word update for my team who have not seen this project, as a bulleted email" beats "summarize this."
• Point it at your own stuff. With Personal Intelligence on, "based on my emails with Sarah" or "using the spreadsheet in my Drive called Q3 forecast" turns a generic answer into a specific one.
• Ask for the disagreement. Add "tell me where experts disagree and what you are least sure about" to any research question. It exposes the guesses.

Before you answer, ask me up to three clarifying questions if anything in my request is ambiguous. Then answer in this format: a two-sentence direct answer first, then the reasoning, then a short list of what could make you wrong. Use plain language and no filler.

25 Things To Try This Week

1. Ask it to plan your week from a calendar summary you provide.
2. Run one Deep Research report on a purchase you are about to make.
3. Build a skill for the email you write most often, then call it with /.
4. Point Live at something broken in your house and ask how to fix it.
5. Ask Gmail to find every unanswered question in your inbox.
6. Generate a product photo with Nano Banana, then Redo with Pro.
7. Make a 10-second video from a photo with Omni (paid plans).
8. Create a song for a friend's birthday with Create music.
9. Upload a PDF and ask for an Audio Overview.
10. Start a Notebook for one project and dump every related chat into it.
11. Use Canvas to write and preview a one-page website.
12. Ask Gemini in Chrome to compare the three tabs you have open.
13. Schedule a Monday briefing.
14. Ask "What's my daily brief?" in Live.
15. Give Tasks a Drive cleanup job and read its report.
16. Use @Google Maps to plan a route with stops.
17. Turn a Deep Research report into a quiz.
18. Ask Guided learning to teach you something you have avoided for years.
19. Make a Storybook for a kid you know.
20. Take a photo of a menu in another language with Live and ask what to order.
21. Ask it to find every commitment you made by email this month.
22. Open Settings > Usage limits to see your allowance and reset time.
23. Read your Gemini Apps Activity page once.
24. Turn on a 3-month auto-delete.
25. Install the desktop app and use Option + Space or Alt + Space ten times in one day.

Where Gemini Is Strongest, And Where It Is Not

Strongest: anything that touches your Google life. Email, calendar, photos, Drive, Maps, YouTube. Deep Research is excellent. The creative tools let you explore ideas alongside the rest of your work. Tasks can handle longer jobs with your connected apps when you have access.

Weaker: long-form writing with real voice still needs a heavy edit. The naming is a mess (two Ultra tiers, two kinds of notebooks, Gems turning into skills, Spark turning into Tasks, models that change version number every month). Usage limits are opaque, and a long chat with attachments can eat a five-hour window fast. Several features are U.S. only or need a personal account, so work accounts and European users get a smaller product. For where Gemini fits next to ChatGPT and Claude, see the only AI tools you need.

Your First Week

• Day 1: Sign in, install the desktop app, review the model picker and set auto-delete.
• Day 2: If eligible, connect the one app you need from Customize and ask a question grounded in it.
• Day 3: Run a Deep Research report and turn it into an audio overview.
• Day 4: Build your first skill and use it three times.
• Day 5: Try Live with the camera on something physical.
• Day 6: Try the image, music or video feature available in your account.
• Day 7: Decide whether Plus, Pro or free is right for how you actually used it.

Pick one thing from the list above, open Gemini, and do it right now. That first result will tell you why Google put this in everything.

Quick Reference

Published March 22, 2026 · Checked October 2026