Gemini Google AI: The Only AI That Handles It All

Welcome to the new video!

Covered in the video:

• The difference between a prompt, prompting, and prompt engineering.

• How personal prompting in chat differs from production prompting used in workflows and products.

Hey everyone, welcome to our first lecture on chat prompting!

Here, you’ll learn how to approach creating and refining prompts that can be used in the chat interface.

Let’s get started!

Covered in the video:

• The core ingredients of an effective prompt, including task, context, tone, and rules.

• When to add grounding and recency instructions for research or fact-based tasks.

• How role and audience context can make Gemini’s responses more relevant and useful.

Hey everyone, welcome back!

If, after watching the previous lecture, you feel like creating a good prompt is an arduous task and that you need to turn into a prompt engineer to succeed in this job, here's a secret the experts use: think of prompting as a conversation or a multi-step process, not a one-time question.

Covered in the video:

• How to improve results by treating prompting as a multi-step conversation rather than a one-off request.

• How to refine Gemini’s answers step by step when drafting, expanding, and polishing content.

• How iterative prompting can also improve accuracy by checking assumptions, sources, and possible weak points.

Hey everyone, welcome back!

Sometimes when you're talking to an AI assistant, it can feel like you're starting from scratch every single time. You can write the perfect prompt and still get a generic answer — because Gemini has no idea who you are or how you work.

Covered in the video:

• The main ways to personalize Gemini, including instructions, memory from past chats, and connected personal context.

• How memory and temporary chats give you more control over what Gemini remembers.

• A preview of Personal Intelligence.

Hi everyone, welcome back!

Covered in the video:

• The main ways to share content with Gemini, including pasted text, uploaded files, images, and links.

• How Gemini can analyze multiple files together and connect information across them.

• What Gemini can do with shared content, such as summarizing, comparing, and extracting useful insights.

Hey everyone, and welcome back to the new lecture where we continue talking about how to communicate with Gemini and what to include in your prompt.

Covered in the video:

• How examples can guide Gemini’s tone, style, structure, and output format.

• How one-shot and few-shot prompting can produce more specific and useful responses.

• How examples can shape not only wording, but also the thinking approach behind the response.

• How interactive examples help you improve outputs through feedback and iteration.

Hey everyone! We are almost done covering the key ingredients of a good prompt.

There’s yet another component you may find worth including in your prompt — information on what format you want the AI’s response to take. Let’s talk about this now.

Covered in the video:

• How to ask Gemini for specific output formats such as reports, tables, lists, and markdown.

• How formatting instructions can make longer answers clearer and easier to use.

• Useful formatting patterns for research, comparison, and decision-making tasks.

Hey everyone! Up until now, we’ve been exploring prompting in isolated pieces.

It’s time to bring those pieces together into a complete, end-to-end workflow.

Covered in the video:

• Learn how to choose between Fast, Thinking, and Pro depending on your task and plan.

• Follow a complete brainstorming workflow from idea generation to trend checking and content expansion.

• See how to ground Gemini with attached source materials to make outputs more specific and useful.

• Learn simple productivity shortcuts like exporting results to Google Docs.

Hey everyone, welcome to the second follow-along video.

Let’s explore getting feedback from Gemini.

Covered in the video:

• Learn how to use Gemini to get feedback on documents, recorded answers, and longer video content.

• Understand how Gemini’s large context window supports richer analysis across long inputs.

• Learn how to turn Gemini’s feedback into the next iteration, such as a stronger interview answer or presentation script.

• Learn simple productivity shortcuts like double-checking responses.

Hey everyone!

Imagine asking an AI assistant about a recent news event, and it confidently cites a detailed article... that doesn't actually exist. Or asking it about public figures and getting responses that mix real facts with completely made-up details.

These aren't bugs or glitches—they're what we call 'hallucinations' in AI, and they're one of the biggest challenges when working with large language models.

Covered in the video:

• What AI hallucinations are and why language models produce plausible-sounding but false information.

• Common warning signs, including overly specific details, perfect-looking citations, inconsistent answers, and overly definitive claims.

• Four strategies to prevent AI hallucinations.

Hey everyone, welcome back to the first lecture of this section!

Covered in the video:

• Understand what Gemini Canvas is and how it differs from the standard chat interface.

• See how Canvas creates a more collaborative workspace for drafting and refining content.

• Get a preview of Canvas capabilities, including document editing, visual generation, study tools, and app building.

As promised, in this video we’re going to get hands-on.

Covered in the video:

• Follow a hands-on walkthrough of creating a new document from scratch inside Gemini Canvas.

• Learn how to make targeted edits with Ask Gemini instead of rewriting the whole draft.

Welcome to the second part of the tutorial on creating and editing documents in Gemini Canvas.

Covered in the video:

• See how Quick Actions can help adjust document length, tone, and overall quality.

• Explore Canvas’s multimodal side by generating supporting visuals alongside your text.

We now have our brand backstory, product features, and images organized within Gemini.

Think of this as our Drafting Studio—the space for core thinking and writing.

However, a working draft isn't a finished deliverable. If you need to present this to a manager or client as a professional report, we need to move this content into a dedicated design tool like Canva or Gamma.app.

Covered in the video:

• See how to transfer text and visuals from Gemini into a design-focused workspace.

• Understand how Gamma helps structure, style, and refine content for a presentation-ready PDF.

Hey everyone! When you start using Gemini regularly, you quickly notice that there are certain things you use it for again and again—whether it’s for brainstorming, getting feedback, or generating new content.

Covered in the video:

• The difference between premade Gems, custom Gems, and experimental Gems from Google Labs powered by Opal.

• How Gems act as specialized assistants for recurring tasks, while Canvas remains the workspace for refining and polishing the output.

Hey everyone, and welcome to our first tutorial on Gemini Gems.

Today, I’m going to show you how to build a custom expert to proofread your writing—whether you’re drafting landing pages, product descriptions, quick emails or any other texts.

Covered in the video:

• Follow a step-by-step walkthrough of creating your first custom Gem for grammar and spelling review.

• Learn how to write clear Gem instructions, including role, rules, and output expectations.

Now, let’s build a Gem that works with video.

Covered in the video:

• Hands-on walkthrough of building a Fitness Coach Gem that analyzes workout videos and gives structured feedback.

• How to combine video analysis with image generation inside one custom Gem.

• See how Gem instructions can be refined to get more consistent results.

Welcome to the second part of the tutorial!

Covered in the video:

• Hands-on walkthrough of building a Fitness Coach Gem that analyzes workout videos and gives structured feedback.

• How to combine video analysis with image generation inside one custom Gem.

• See how Gem instructions can be refined to get more consistent results.

You might have noticed a strange little banana emoji appearing in your Gemini app.

It’s not just a cute icon. It’s a tiny clue to a funny naming story behind this model.

Covered in the video:

• What “Nano Banana” is and how the nickname became attached to Google’s image model.

• The model’s standout features, including character consistency, scene blending, multi-turn image editing, and design mixing.

So now that you saw the preview of Gemini’s visual capabilities, let’s create our first image. Image creation is available on all plans.

Covered in the video:

• Two simple ways to create images in Gemini: inside an existing chat or from a new chat.

• How to improve an image step by step through follow-up prompts and branch off from an earlier version when needed.

• The difference between Fast and Thinking modes, and when each one makes the most sense.

As this section of the course is all about generating visuals, we cannot overlook such an important topic as how to create those instructions.

Covered in the video:

• Seven practical tips for writing effective prompts to generate better visuals.

Today, we’re going to look at how to use images to "talk" to the AI.

Covered in the video:

• Contextual blending for placing a product into a new creative scene while keeping it realistic.

• Iterative refinement for improving one visual step by step instead of trying to get it perfect in one prompt.

• Visual synthesis for combining many separate assets into one cohesive campaign-style image.

Hey everyone and welcome back to the series of lectures on creating images with Gemini!

In this video we’re heading into the Gemini’s editing capabilities.

Covered in the video:

• Turning rough sketches into more complete visual prototypes.

• Restoring older or lower-quality photos by improving clarity, detail, and color.

• Using Gemini’s image reasoning to reinterpret and upgrade existing visuals.

Welcome to the second part of the tutorial where we explore Gemini’s editing capabilities.

Covered in the video:

• Editing specific parts of an image with Gemini’s Markup tool.

• Refining images further through follow-up conversational edits.

• Bringing in annotations from external tools like Canva to guide more precise changes.

Welcome back! So far, we've covered a lot of things — creating from scratch, editing with precision, and synthesizing complex scenes.

Now let's look at what Gemini can do when the task gets even more ambitious: building multi-piece visual assets like menus, diagrams, and assets that work across different social platforms and screens.

Covered in the video:

• Creating one-page visual assets like menus and infographics from multiple input images.

• Turning a written process into a clean visual diagram with icons, structure, and branded colors.

• Refining the style of specific visual elements to make diagrams clearer and more approachable.

• Translating text inside an image into another language.

Welcome to the second part of the tutorial on creating complex visuals with Gemini!

Covered in the video:

• Extending and re-composing an image so it works across vertical, square, and wide layouts.

Welcome to the first lecture of this section!

Covered in the video:

• What “Blueprint Answers” are and why they often feel too shallow for important questions.

• How Deep Research goes beyond a standard chatbot by planning, searching, reasoning, and synthesizing information into one report.

• Three main use cases: understanding complex topics, doing professional due diligence, and supporting high-stakes personal decisions.

• What the final Deep Research output looks like, including structured analysis, cited sources, and more visual ways of presenting findings.

As promised, let's see Deep Research in action.

We're going to start with the Topic Understanding use case.

Covered in the video:

• Launching Deep Research from a new chat and choosing which sources it can use.

• Writing a focused research prompt with several clear goals instead of one vague question.

• How Fast, Thinking, and Pro affect the depth and style of the research process.

• The research planning step, where Gemini breaks the task into a multi-step investigation before searching.

• How Deep Research searches, cross-checks, reroutes around dead ends, and keeps the full thread of the research in memory.

• What the final report looks like: a structured, multi-page analysis with cited sources and actionable conclusions.

In this and the following lecture, we're going to look at two more use cases for Deep Research that I think you'll find immediately useful in your own life.

Covered in the video:

• Using Deep Research to compare products based on a personal buying decision.

• Reviewing and adjusting the research plan before Gemini starts searching.

• Getting a structured shortlist with a comparison table covering product features, pricing, long-term cost, etc.

Welcome back!

Covered in the video:

• Using handwritten notes as the starting point for a Deep Research report.

• Turning existing study material into a deeper, structured analysis of a new subject.

• Converting the final report into an infographic, a quiz, and flashcards inside Gemini.

Welcome back! So in our last Canvas lecture, we focused on document drafting — how Canvas gives you a live workspace to refine writing with Gemini right beside you.

But document drafting is really just the beginning of what Canvas can do.

Covered in the video:

• How Canvas connects with Deep Research and becomes the workspace for turning reports into other formats.

• Creating web pages, infographics, quizzes, and flashcards from existing content inside Canvas.

• Using audio overviews to turn written material into a podcast-style summary.

• Building functional apps in Canvas by describing what you want instead of writing code.

Welcome back! Here we're building a breakfast chef app — quick meals under 20 minutes, family-friendly, with photos of the finished dish.

All inside Gemini Canvas. No code, no technical background needed. Just a good prompt and a bit of back-and-forth with Gemini.

Covered in the video:

• Four-step process of building an app with Gemini

• Brainstorming the app’s purpose, features, and overall look before building.

• Choosing the right model for app creation inside Canvas.

• Starting building inside a Deep Research report vs creating an app from scratch

• Refining the first version of the app through follow-up prompts and iterative changes.

Welcome to the second part of the tutorial!

Covered in the video:

• A walkthrough of the Canvas Toolbar and the different ways it can refine an app.

• Using the AI Feature Injector to add new smart capabilities to the app.

• Making targeted changes with the refinement tool and seeing how prompt wording affects the result.

• The difference between broad visual changes and tightly scoped edits.

• Sharing the finished app with others through a browser-based link and remixing workflow.