Posted by Apple Podcasts ¦ Amazon Music ¦ Spotify
Hi, and welcome to Try AI for Growth, a podcast out of Make Space for Growth.
Here, I share short, and sometimes surprising stories of how I’ve used AI to tackle real challenges at work and at home.
I’m your host, Sara Vicente Barreto, and today I want to tell you about how AI helped my daughter go from feeling stuck in her biology revision… to scoring above 90% in just a few hours. This time, the tool we used is one I’ve mentioned before, but in a very different context: Google Notebook LLM.
The Problem
So here’s what happened. It was the weekend, and my daughter was preparing for a biology test. She was not feeling confident at all. There have been frequent teacher changes, lots of slides uploaded into Google Classroom, and she was feeling a bit lost.
Too many concepts.
Too many diagrams.
Too many things that “kind of made sense” but didn’t fully click.
So she did what more and more kids are doing now. She turned to GenAI. She was using a regular GenAI to get flashcards, practice quizzes and other explanations. Which, in theory, is great. But in practice? It was too much. The answers were too broad, not fully aligned with her syllabus, and also introduced concepts she had not yet learned. So instead of simplifying things… it was adding noise.
And that’s an important point. Sometimes AI doesn’t fail because it’s wrong, it fails because it’s too general. She wasn’t lacking effort. She was lacking focus.
The Approach
This is where I introduced her to Google Notebook LLM. Proud mama moment. I had used this tool before, for example, to turn a report into a podcast or to structure information from documents. But the original purpose of this tool was indeed to help process large amounts of information and support students in their studies.
In fact, Google Notebook LLM is a focused study environment. The difference is simple, but powerful. Instead of asking AI about everything… you constrain it to just your materials.
So here’s exactly what we did. We uploaded her Google Slides from school, screenshots of her work and notes, and specific content on the respiratory system, which was the area of focus.
The thing with Google Notebook LLM is that you barely need to prompt. It has a series of built-in solutions that you can just guide. You can:
- Generate flashcards for practice from the materials
- Create a video focused on the respiratory system
- Provide a quiz to test her abilities
- Generate a mind map of the concepts she needed to grasp
- Provide an infographic
All this is available through a click and a few seconds. Oh, and free.
The Output
Immediately, everything became more relevant. Because the model was grounded in her content.
At the centre of the Notebook, you have a bot that you can query. It was powerful for her to start asking questions in areas that she did not understand as much. Things like:
“What’s the difference between arteries and veins again?”
Now, instead of a generic explanation, she was getting answers based on her materials. And that completely changed the experience.
It was also powerful when the answer was not in the content she provided. There was no hallucination; the bot just said it did not have the information to reply. We searched elsewhere for base materials, uploaded them again, and suddenly the answer was possible. All practical and super intuitive.
The Outcome
When we started, she was nervous that she was only getting a quarter of the answers on the flashcards right. That made her even more anxious. Once she had gone through a few videos and chatted to the bot (aka tutor), she tested herself again.
She scored above 90%. In only a few hours.
But honestly, the score wasn’t the most important part. The real shift was going from panic and overwhelm to structure and support.
Obviously, I was immensely proud that I was the one bringing this tool to her. It is well known for older students, but it apparently had not reached her yet (and was blocked on her school iPad).
The other great outcome was that she understood the world of GenAi can sometimes be unhelpful because not only does it have too much information when she is trying to focus on her syllabus, but also it has a great danger of hallucinating information when it does not know the answer. That did not happen in Notebook LLM.
This will not be a one-off. It is a shift in how learning can happen.
Lessons for Today
There are a few things this really highlighted for me.
1. Context beats capability – AI is incredibly powerful, but without boundaries, it becomes overwhelming. By limiting the LLLM to her materials, we didn’t make it weaker; we made it useful.
2. AI can adapt to how you learn – We often think of AI as text-based. But here, it became visual, interactive and personal. Because we shaped it around her learning style and the needs she had.
3. Conversation AI becomes a partnership – The power was not only in the quiz or the flashcards (though that really helped). It was when she started asking questions. That back-and-forth, that curiosity, the quick answer. That provides huge versatility.
What You Can Try
This goes far beyond studying. It isn’t just about school. It’s about how we interact with knowledge. When you narrow the scope, provide the right inputs and stay engaged, AI becomes more than a nice tool. It becomes a real-time colleague.
In companies with vast amounts of contextual information, it can be just as powerful. So if you’re wondering how to apply this, here are a few simple ideas, beyond helping your kids study. You can apply the same approach to:
- Training manuals
- Process documentation
- Internal playbooks
- Onboarding process
Done right, you may not even need a fancy agent. You can have your procedure manual uploaded and, when someone is asking a question, you can immediately check in with the bot. All while providing different sources of training that can adapt to the cognitive preference of each employee. The answers will be solely based on your company’s knowledge. No searching. No outdated versions. No hallucinations. Just relevant answers.
This was a small experiment—but a powerful one. Because it showed me that the value of AI is not always in doing more. AI can be distracting in the way that it makes the whole world accessible to us. But the value can be in doing things with more focus.
In this case, that made all the difference.
So if you’re feeling stuck—whether it’s studying, learning, or managing information— try this approach. Don’t overdo it the first time around. Just try it. You may improve your process, your outcome, and have a whole different experience of processing large amounts of information.
Thanks for joining me on this episode of Try AI for Growth. If you try something similar, I’d genuinely love to hear how it goes.
If you can, share this episode with someone who may be struggling with enhancing learning processes. The more you share, the more we will all learn!
Until next time—keep experimenting and keep having fun.
Photo by August de Richelieu – Pexels