back

How to Use Gemini AI’s Deep Research to Save HOURS

Artificial intelligence is changing the way we approach research, and Google Gemini AI is one of the latest AI tools designed to help with deep research and academic writing. In this video, I explore how to use Gemini AI for gathering and organizing information, analyzing sources, and even generating structured summaries. ▼ ▽ Sign up for my FREE newsletter Join 21,000+ email subscribers receiving the free tools and academic tips directly from me: https://academiainsider.com/newsletter/ ▼ ▽ MY TOP SELLING COURSE ▼ ▽ ▶ Become a Master Academic Writer With AI using my course: https://academy.academiainsider.com/courses/ai-writing-course One of the most impressive aspects of Gemini AI is its ability to create research plans based on a single prompt. Unlike other AI models that require back-and-forth conversations, Gemini generates a structured workflow almost instantly. This is where prompt engineering becomes critical—how you phrase your query directly impacts the quality of results you get. The better the prompt, the better the research plan. But is it as deep as it claims to be? I put it to the test with a few unusual topics to see if it really delivers on its promise. If you’re wondering how to get started with Gemini AI, the process is relatively straightforward, but there are some key features you need to be aware of. For example, while it does an excellent job of retrieving and summarizing content, it doesn’t always provide traditional academic citations. That means, if you’re using it for academic research, you might still need to cross-check sources manually. However, its ability to generate structured tables and export reports into Google Docs makes it a highly efficient assistant for organizing information. Throughout the video, I share my honest impressions, including what Gemini gets right and where it still has room for improvement. If you’re curious to try Gemini AI for your own research, this breakdown will give you a clear idea of what to expect. Whether you’re a student, researcher, or just someone interested in AI tools, this is an exciting glimpse into the future of academic work. ………………………………………… ▼ ▽ TIMESTAMPS 00:00 Intro 00:07 Gemini AI 00:32 Research Test 01:33 Edit Plan 02:11 The Results 02:45 Asking About Transparent electrodes 05:30 Table Function 06:45 Bugs at the moment 07:43 Do Research Write Literature Review? 08:56 Conclusion 09:14 Outro ………………………………………… ▼ ▽ Socials for shorts and reels Instagram: https://www.instagram.com/drandystapleton/ TikTok: https://www.tiktok.com/@drandystapleton

Recent Videos

May 6, 2026

Hermes Agent Master Class

https://www.youtube.com/watch?v=R3YOGfTBcQg Welcome to the Hermes Agent Master Class — an 11-episode series taking you from zero to fully leveraging every feature of Nous Research's open-source agent. In this first episode, we install Hermes from scratch on a brand new machine with no prior skills or memory, walk through full configuration with OpenRouter, tour the most important CLI and slash commands, and run our first real task: a competitor research report on a custom children's book AI business idea. Every future episode will build on this fresh install so you can see the compounding value of the agent in real time....

Apr 29, 2026

Andrej Karpathy – Outsource your thinking, but you can’t outsource your understanding

https://www.youtube.com/watch?v=96jN2OCOfLs Here's what Andrej Karpathy just figured out that everyone else is still dancing around: we're not in an era of "better models." We're in a different era of computing altogether. And the difference between understanding that and not understanding it is the difference between being a vibe coder and being an agentic engineer. Last October, Karpathy had a realization. AI didn't stop being ChatGPT-adjacent. It fundamentally shifted. Agentic coherent workflows started to actually work. And he's spent the last three months living in side projects, VB coding, exploring what's actually possible. What he found is a framework that explains...

Mar 30, 2026

Andrej Karpathy on the Decade of Agents, the Limits of RL, and Why Education Is His Next Mission

A summary of key takeaways from Andrej Karpathy's conversation with Dwarkesh Patel In a wide-ranging conversation with Dwarkesh Patel, Andrej Karpathy — former head of AI at Tesla, founding member of OpenAI, and creator of some of the most popular AI educational content on the internet — shared his views on where AI is headed, what's still broken, and why he's now pouring his energy into education. Here are the key takeaways. "It's the Decade of Agents, Not the Year of Agents" Karpathy's now-famous quote is a direct pushback on industry hype. Early agents like Claude Code and Codex are...