When a human tries to learn something new, one single training session is not very effective.
Why? Because the human brain forgets things. Pretty quickly and reliably. After 48 hours, most of the information you received is gone.
There are many ways to combat the forgetting curve including note-taking, flash cards, and continuing to the next training session to build your knowledge.
With the rise of AI tools, we now have a new way to extend a single training session: personalized learning chatbots.
This new emerging technology allow learners to “revisit” prior learning experiences and interact with the material in their own way, at their own pace.
Learners can ask a chatbot questions specifically about their training session, helping them unlock particular challenges tailored to their unique needs.
That one single training session can be transformed into a continuous learning process that is on-demand and customized for that specific learner.
In this post, I’ll guide you through the steps of creating your own personalized learning chatbot and explore how this approach can be applied in areas like customer education, sales enablement, and corporate training.
Why personalized learning matters
The traditional way we’ve approached training and learning is inefficient. It’s designed for the widest audience possible, following a standardized approach.
From traditional classroom settings to corporate training programs, the default has been to create a single set of materials that aim to serve everyone. It was the only scalable way. This standardized approach to training and learning has significant limitations.
Every human is different. People learn at different paces, have varied backgrounds, and bring unique sets of prior knowledge and experience.
A one-size-fits-all approach doesn’t account for the level of knowledge the audience has. Some people may need extra time to learn a concept, while others may already be familiar with the basics and are ready to advance.
This can lead to disengagement, as slower learners feel overwhelmed, while quicker learners feel bored and unchallenged.
The shift toward personalized learning
Over the years, we’ve seen efforts to make learning more personalized. Think about the rise of learning platforms like Duolingo and Khan Academy, which use data to adjust lessons based on a learner’s progress.
Online education has opened the door for students to select courses aligned with their interests and skill levels. Corporate training programs often use self-paced training content that allows employees to progress through materials at their own speed.
The concept of personalized learning took a significant leap forward with these innovations, making learning more engaging by offering content that is better suited to an individual’s needs.
Now, we’re in the midst of an AI revolution that is completely reshaping personalized learning. AI-powered tools like chatbots can offer real-time, customized interactions that adapt to each user’s specific questions and learning needs.
With tools like Google’s NotebookLM, a user can ask a chatbot about particular features or concepts and receive responses tailored directly to their inquiries.
This shifts learning from being a static, passive experience to an interactive, dynamic one. It’s no longer just about pushing generic content to learners in broad strokes. It’s about providing a responsive, on-demand guide that supports their unique journey.
AI is allowing us to move beyond standardization, making personalized learning more accessible and effective than ever before.
Plus, it’s shockingly simple to create your own personalized learning chatbot using free AI tools. Here’s how to do it:
Step-by-Step Guide to Creating Your Own Personalized Learning Chatbot
1. Record video (or audio) of an expert teaching a topic
Your personalized learning experience starts with the source material…a recorded video (or audio) of a training session or expert demonstration.
This could be any subject you want to learn. In your personal life, this could be a video of a golf lesson, a dog training, or any other hobby you’re looking to learn.
At your job, this could be a recorded product demo, sales training, onboarding video for new hires, or a live training held on Zoom (assuming your company policy allows for data to be analyzed by 3rd party companies).
Recording a video is key because it captures the organic nuances and personalized feedback in the lesson, which are often lost in written materials.
2. Get a text transcript of your video
AI chatbots work best with text inputs, so I recommend converting your video into a text transcript. This helps the chatbot to better understand and draw from the information.
My favorite tool for video to text transcript is Descript. But there are many others like Otter.ai, or Rev can easily do transcriptions. Your output should be a clean text file (like a Google doc or Word Doc). This will be the resource your personalized learning chatbot will have to pull from.
3. Upload the transcript to NotebookLM
Now that you have a text transcript, it’s time to create your personalized learning chatbot using NotebookLM.
Simply create a new notebook. Then, upload the transcript as a source. This means that your chatbot’s main data source is now your unique learning experience.
For example, if your transcript mentions your dog’s name and specific training techniques, the chatbot will use those details in its answers. This way, your AI chatbot provides a learning experience tailored specifically to you.
4. Interact with your personalized learning chatbot
Once your chatbot is set up, you can start interacting with it by asking questions.
Remember, your chatbot’s main data source is your unique video transcript with your specific pain points and nuances. Any answer the chatbot provides will be customized to your experience.
This creates a meaningful interaction, personalized for the learner. Something we’ve never seen before in the realm of digital learning. It allows you, the learner, to take a single training session and turn it into a continuous learning process you can revisit and practice 24/7 whenever you need it.
How personalized learning chatbots align with human learning science
This all sounds great in theory, but how do these personalized learning chatbots align with learning science? Personalized learning chatbots support several well-established theories of human learning.
These theories, which have guided instructional design for decades, emphasize the importance of active engagement, timely feedback, and learning that adapts to the unique needs of each learner.
Let’s explore some of these theories and how personalized chatbots can directly support or enhance the learning process.
1. Constructivist Learning Theory
Constructivism suggests that learners construct new knowledge based on their prior experiences and understanding. This theory highlights the importance of learners actively engaging with new information, making connections to what they already know, and building their own understanding.
Personalized learning chatbots fit well within this framework. Rather than passively receiving information, learners can interact with a chatbot, ask questions, and receive responses that build on their existing knowledge.
For example, if a learner is training on a new software tool, they can use a chatbot to dive deeper into areas they find confusing, asking specific questions that help them relate new concepts to their existing experience with similar tools. This allows the learner to construct a deeper understanding of the subject matter at their own pace, creating a more meaningful learning experience.
2. Cognitive Load Theory
Cognitive Load Theory (CLT) focuses on the limitations of working memory and the need to optimize information delivery for effective learning. If too much information is presented at once, it can overwhelm the learner’s cognitive capacity, leading to frustration and ineffective learning.
Personalized learning chatbots can mitigate cognitive overload by allowing learners to control the pace and flow of information. Instead of being overwhelmed by a dense training manual or a long video tutorial, users can ask targeted questions and receive just-in-time answers for their immediate needs.
For example, if a new hire at a company is learning about company policies, instead of memorizing a lengthy document, they can use the chatbot to ask questions as they arise during their daily tasks. This reduces the cognitive load by breaking down information into manageable chunks, allowing the learner to focus on what’s relevant at the moment, improving retention and understanding.
3. The Zone of Proximal Development (ZPD)
The Zone of Proximal Development (ZPD) suggests that learners benefit most when they are guided through tasks that are slightly beyond their current abilities but achievable with support.
In traditional education, this support often comes from a teacher or mentor. With a personalized learning chatbot, the chatbot itself can serve as a virtual mentor, providing guidance tailored to the learner’s current understanding.
When a user asks questions to a chatbot, the chatbot can adapt its responses based on the user’s level of understanding, delivering explanations that are neither too simple nor too complex. This aligns with the ZPD by keeping the learner in that ideal space where they can grasp new concepts with a little guidance.
For example, in customer education, a chatbot can provide advanced users with in-depth technical explanations while offering simpler, step-by-step guidance to beginners, ensuring that each learner gets the support they need.
4. Self-Determination Theory (SDT)
Self-Determination Theory emphasizes the importance of autonomy, competence, and relatedness in motivating learners. Learners are more engaged when they feel they have control over their learning process and when their learning experience aligns with their interests and needs.
Personalized learning chatbots offer a high level of autonomy by allowing learners to explore topics at their own pace and ask questions that are specifically relevant to them.
For example, in a corporate training context, a sales representative using a chatbot can ask highly specific questions about sales strategies or product features that matter most to their daily work, rather than following a generic training program.
This autonomy helps keep them engaged, as they feel empowered to direct their learning experience and focus on areas where they want to improve. By providing instant feedback and tailored answers, the chatbot can help learners feel a sense of competence as they gain new skills.
5. Retrieval Practice and Spaced Repetition
“Retrieval practice” involves recalling information from memory, and is a key part of effective learning. This technique is often combined with “spaced repetition,” reviewing material at spaced intervals over time to strengthen memory retention.
Personalized learning chatbots can be powerful tools for supporting retrieval and spaced repetition. When a learner interacts with a chatbot to review concepts or revisit specific parts of their training, they are engaging in retrieval practice.
For example, after completing an initial training session on using a new CRM platform, a salesperson can use the chatbot to periodically review certain features or best practices, reinforcing what they’ve learned over time.
This ability to repeatedly engage with a chatbot at different intervals supports the principles of spaced repetition, helping to solidify long-term retention of the training content. As a result, learners are more likely to retain the information and apply it effectively in their roles.
Applications of Personalized Learning in Corporate Training
Personalized learning chatbots (while still new) have potential to transform how businesses approach training and education. Here’s how it could play out:
Customer Education
Imagine a customer support team that’s just been trained on a new software product. They’ve gone through a training session that addresses their specific setup.
Instead of sending them back to generic help documentation, you can give them access to a personalized learning chatbot trained on their unique training materials.
The team can ask questions like, “How do I configure feature X for our needs?” and get detailed answers specific to their environment. This makes customer onboarding smoother, as the chatbot offers an experience that feels custom-made for the user.
Sales Enablement
Sales teams often encounter unexpected questions or challenges while on the go. A personalized learning chatbot can be trained on a library of sales materials or product demos, giving reps instant access to the information they need.
If a sales rep is prepping for a client meeting and needs a refresher on product specs, they can ask the chatbot and receive an accurate response in seconds. This empowers sales teams with knowledge at their fingertips, improving their ability to close deals and build client relationships.
Corporate Training and Employee Onboarding
In corporate training, a personalized learning chatbot can transform a one-time session into an ongoing educational resource.
For example, new hires can use a chatbot to revisit training content and ask specific questions about company processes or tools. This continuous access to training materials helps new employees feel more confident as they adapt to their roles. This new approach to onboarding that offers a personalized touch, makes learning more engaging and effective.
Final Thoughts
As AI continues to evolve, personalized learning is set to become the standard in learning and training. Chatbots like those built with Google’s NotebookLM make it easy to create these tailored learning experiences, allowing users to ask questions and get targeted answers that address their needs. For SaaS companies, this means the potential to enhance product adoption, improve customer retention, and deliver a more engaging user experience.
If you haven’t yet explored the power of personalized learning chatbots, now is a great time to start. With intuitive tools and a straightforward setup, you can transform your training and onboarding processes.
