Gemini is quietly crushing it — 7 prompts that prove what the model can do
Unlock more from Gemini with these prompts
Here at Tom’s Guide our expert editors are committed to bringing you the best news, reviews and guides to help you stay informed and ahead of the curve!
You are now subscribed
Your newsletter sign-up was successful
Want to add more newsletters?
Daily (Mon-Sun)
Tom's Guide Daily
Sign up to get the latest updates on all of your favorite content! From cutting-edge tech news and the hottest streaming buzz to unbeatable deals on the best products and in-depth reviews, we’ve got you covered.
Weekly on Thursday
Tom's AI Guide
Be AI savvy with your weekly newsletter summing up all the biggest AI news you need to know. Plus, analysis from our AI editor and tips on how to use the latest AI tools!
Weekly on Friday
Tom's iGuide
Unlock the vast world of Apple news straight to your inbox. With coverage on everything from exciting product launches to essential software updates, this is your go-to source for the latest updates on all the best Apple content.
Weekly on Monday
Tom's Streaming Guide
Our weekly newsletter is expertly crafted to immerse you in the world of streaming. Stay updated on the latest releases and our top recommendations across your favorite streaming platforms.
Join the club
Get full access to premium articles, exclusive features and a growing list of member rewards.
When Gemini first launched, I wasn’t sold. I tested it early, ran into a few hallucinations, and quickly went back to ChatGPT or Claude for anything that really mattered.
Fast forward to now, and Gemini feels like a different tool. Google has quietly rebuilt it into something far more capable — with stronger reasoning, true multimodal inputs, and features that actually change how you use AI day to day. Curious whether the hype finally matched reality, I started pushing Gemini with more demanding prompts.
That’s when it surprised me. Gemini didn’t just answer questions — it collaborated, adapted, and handled complex tasks with ease. At this point, it’s one of the most powerful AI platforms available, especially if you know how to prompt it properly.
Here are seven Gemini prompts that completely changed how I use it.
1. Summarization
Prompt: “Summarize today’s top 3 AI news stories in plain English, and include links to credible sources.”
This is one of my favorite prompts because it utilizes all of Gemini's strenghths. From real-time web access (Gemini can actually pull in fresh reporting) and then summarize multiple articles into digestible insights. Even if it's a breaking story in non-English outlets, Gemini has you covered with multilingual abilities.
And, by requiring links to credible sources, this prompt nudges Gemini to show you exactly where it got its information. This is extremely important for verifying facts directly.
2. Update images
Prompt: "Take this photo of me and turn it into a Pixar-style movie poster — keep the outfit consistent, add dramatic lighting, and bold text at the top with the title ‘The AI Adventure.’"
This prompt can be reused a number of times, but it is essentially showcasing just how well Gemini's Nano Banana works for image generation. Gemini now offers 100 free image generations per day within the free tier, so you can create a number of different images easily.
3 Video generation
Prompt: “Create a vertical 9:16 video of a futuristic city street at night, neon signs glowing, people walking, and flying cars overhead — add ambient city sounds.”
I've created a number of videos using Veo 3, both within Google's AI studio and even in Canva Pro. Whether you use this one or one of your own, it's easier than ever to create videos.
One pro tip is to be sure you choose Veo 3 and not Veo 2 when you're in Google's AI studio because the default is Veo 2 and the generation may not contain sound otherwise. Because tonkens are limited, even with Ultra, you're going to want to be sure to get your prompt right before diving in.
4. Gemini Live
Prompt: "Act as my French tutor: ask me simple questions in French, let me answer by speaking, then correct me gently and continue the conversation.”
One of the best Gemini features is Gemini Live on the app. When you use it you can speak directly to the chatbot and it delivers human-like responses. It can even see the world around you, which makes the conversation even more realistic.
Try this prompt or a similar one with Gemini Live to get the most out of the chatbot's response. It will respond like a human helping you to craft your language skills with ease.
5. Deep research
Prompt: “Do a comprehensive literature review on how AI assistants are affecting workplace productivity. Summarize at least 5 peer-reviewed studies from the past 3 years, highlight key findings, note any conflicting results, and include links or citations to the original sources.”
Gemini Deep Research is a way to go even deeper than the surface level responses from the chatbot. Now, when you want to research a topic, you can easily do so with a single prompt. Deep reseraching takes a little bit longer, but Gemini will let you know when it is done and even create a Google Doc with all the information organized for you to keep and peruse.
6. Coding
Prompt: “Here’s a snippet of Python code [paste code]. Explain why it’s failing, fix it, and show me how to optimize it for speed.”
This prompt is a great way to see just how well Gemini can vibe code through reasoning and models that can fine-tune with speed. So whether you want the model to completely write new code for games, websites or applications or simply troubleshoot something you currently are using, Gemini has you covered.
7. Mulitmodal abilities
Prompt: “Generate a travel itinerary for a family of five visiting Boston for 3 days. Include a daily schedule, realistic restaurant options, and create one image of what Day 2’s highlight (the Freedom Trail walk) would look like.”
Because Gemini can access information in real time, it can be very helpful when planning vacations. WIth a prompt like this you can get a detailed itinerary for just about anywhere in the world. Because Google AI can now book a table for you and make other calls for you, that's one aspect of the trip you won't even need to worry about.
Final thoughts
Gemini has quickly grown from a renamed chatbot into a sprawling AI ecosystem that now spans text, images, video, audio and code. With models like Gemini 2.5 Pro pushing reasoning benchmarks, Nano Banana redefining image editing, and Veo 3 making video generation practical for creators, Google is clearly betting big on multimodality.
While all the models and the naming itself can be confusing, the trajectory is unmistakable: Gemini is much more than a competitor to ChatGPT and in a league of it's own.
More from Tom's Guide
- Apple is not throwing in the AI towel with Google deal — 'Apple is building its own models based on Gemini that will power a more advanced version of Siri' says analyst
- Apple and Google reach deal to power Siri with Gemini — and it could change the iPhone forever
- 9 signs Google’s Gemini just ended ChatGPT’s dominance
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.

Amanda Caswell is an award-winning journalist, bestselling YA author, and one of today’s leading voices in AI and technology. A celebrated contributor to various news outlets, her sharp insights and relatable storytelling have earned her a loyal readership. Amanda’s work has been recognized with prestigious honors, including outstanding contribution to media.
Known for her ability to bring clarity to even the most complex topics, Amanda seamlessly blends innovation and creativity, inspiring readers to embrace the power of AI and emerging technologies. As a certified prompt engineer, she continues to push the boundaries of how humans and AI can work together.
Beyond her journalism career, Amanda is a long-distance runner and mom of three. She lives in New Jersey.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.










