Google Gemini

Google's AI assistant, woven into Gmail, Drive, Maps and YouTube: Deep Research, Canvas, Gems, images, video and the Spark agent. A free mini-course from basics to power moves.

Whisperer's verdict: 4.3 / 5

What it nails

Watch out for

Gemini is Google's AI assistant, on the web, Android, iOS, Mac and, since 10 September 2026, Windows (press Alt + Space). Its superpower is Google itself: it can search the web, read your Gmail and Drive when you allow it, plan on Maps, make images and videos, and run agents that work for you in the background.

Gemini Spark | I/O 2026 Keynote (Google)

Start here: the basics

  1. Open gemini.google.com or the app and sign in with your Google account.
  2. Talk to it naturally. Google's advice: "Talk to Gemini just like you would a friend or colleague."
  3. Give context. "The more context you give to Gemini, the better it can understand your request."
  4. Break big jobs apart. "If you want Gemini to perform several related tasks, break them apart into separate prompts."
Training plan

Example by Google · source ↗ · Google's own before example.

Write a training plan for the sales team for the launch of a brand new product.

Example by Google · source ↗ · The improved version from Google.

Google's prompt formula: Persona, Task, Context, Format

Google's Prompting guide 101 builds every great prompt from four parts, and notes that "the most successful prompts average around 21 words".

You are a Google Cloud program manager. Draft an executive summary email to [persona] based on [details about relevant program docs]. Limit to bullet points.

Example by Google Prompting guide 101 · source ↗ · Replace the brackets with your own details.

Make this a power prompt: [original prompt text here]

Example by Google Workspace · source ↗ · Google's own trick: paste your rough prompt where the brackets are.

Which model and plan to pick

Gemini 3.8 Flash (2 September 2026) is Google's "best reasoning and coding model yet" and runs in the app for AI Pro and Ultra. Free users get Gemini 3.6 Flash and varying access to 3.1 Pro. Gemini 3.5 Pro is announced as "coming soon".

PlanPrice (US)What you get
Free$03.6 Flash, varying 3.1 Pro, images, Deep Research, Live, Canvas, Gems, 32k-token context
Google AI Plus$4.99 / month2x Free limits, video generation, Gemini in Gmail, 128k context, 400 GB storage
Google AI Pro$19.99 / month4x Free limits, 1M-token context, Spark agent, Jules coding agent, 5 TB storage
Google AI Ultra$99.99 or $199.99 / month5x or 20x AI Pro limits, Deep Think, 20 TB+ storage

Limits refresh every 5 hours until you reach a weekly limit. Eligible college students can get a year of AI Pro (US) or AI Plus free.

Power moves

1. Gems: your own custom experts

Gems are "custom AI experts for help on any topic", from a career coach to a coding helper. They "save highly detailed prompt instructions for your most repeatable tasks", so you write the perfect prompt once. Free plan included.

2. Deep Research: a report in minutes

Deep Research "can automatically browse up to hundreds of websites and even your Gmail, Drive and Chat on your behalf" and write "insightful multi-page reports in minutes". Turn a report into a quiz, a Canvas page or an audio overview.

3. Canvas: from prompt to prototype

"Bring your ideas to life as apps, games, infographics and more. Go from prompt to prototype in minutes." Canvas also drafts and polishes long writing.

4. Connected apps and Personal Intelligence

Connect Gmail, Calendar, Keep, Maps and YouTube Music, plus partners like Canva, OpenTable and Dropbox. With Personal Intelligence (opt-in) Gemini uses your past chats and connected apps to answer about your life.

create a calendar event based on those details

Example by Google · source ↗ · Take a photo of an event flyer, attach it, then send this.

5. Images that know the world

Gemini makes and edits images with Nano Banana 2: text inside pictures, translations, and scenes built from live search.

Create an infographic that shows how to make elaichi chai

Example by Google · source ↗

Search for current weather and date in San Francisco. Analytically, use this data to modify the scene (e.g., if raining, make it look grey and rainy). Visualize this in a miniature city-in-a-cup concept embedded within a realistic, modern smartphone UI.

Example by Google Cloud · source ↗

translate all the English text on the three yellow and blue cans into Korean, while keeping everything else the same

Example by Google · source ↗ · This is an edit: upload your product photo first.

Create a riveting epic 9 part story with 9 images with these two protagonists and their adventures as secret superheroes. The story is thrilling throughout with emotional highs and lows and ending on a great twist and high note. Do not include any words or text on the images but tell the story purely through the imagery itself.

Example by Google · source ↗ · This is an edit: upload photos of your two heroes first.

Using the attached napkin sketch as the structure and the attached fabric sample as the texture, transform this into a high-fidelity 3D armchair render. Place it in a sun-drenched, minimalist living room.

Example by Google Cloud · source ↗ · This is an edit: attach your sketch and a fabric photo first.

6. Spark: an agent that works 24/7

Gemini Spark is "your personal AI agent" that "takes action on your behalf and under your direction, handling tasks 24/7" across Gmail, Calendar, Drive and more. Connections are "turned off by default". AI Pro and Ultra, 18+.

7. Gemini Live: talk and show

Speak with Gemini, switch to typing in the same chat, and share your camera so it can see what you see.

Gemini "may produce inaccurate or offensive information". Google also says: "Please don't enter confidential information that you wouldn't want a reviewer to see". For Spark, Google's own rule is "Supervise closely, interrupt when needed." Some features are not available in the EEA, UK, Switzerland or Nigeria.

FAQ

Is Gemini free?

Yes. The Free plan includes Gemini 3.6 Flash, image creation, Deep Research, Canvas, Gems and Gemini Live, with usage limits.

What is the difference between Gemini and Nano Banana?

Gemini is the assistant. Nano Banana 2 is the image model it uses to create and edit pictures.

How long a document can Gemini read?

32k tokens on Free, 128k on AI Plus and 1 million on AI Pro and Ultra.

Can Gemini make videos?

Yes, with a Google AI subscription: Gemini Omni turns text, photos or video into 10-second clips with sound.

Is there a Gemini app for Windows?

Yes, since 10 September 2026. Press Alt + Space to open it from anywhere.

Sources: Gemini release notes · Google AI plans · Gemini 3.8 Flash · Gemini limits · Gemini Deep Research