Vibe Coding Sparked a Love of Reading in My Classroom

I’ve had huge concepts earlier than. Concepts that felt pressing and essential at 11 p.m. and in some way evaporated by morning. So, when the concept for creating an AI-powered studying suggestion system to generate pupil pleasure about our college’s library catalog got here to me, I requested my accomplice what she thought of me giving up evenings and weekends for a 12 months or two. “Simply go for it,” she mentioned.

That dialog was in Might 2025. By November, my vibe-coded app was dwell in my classroom.

Why I Began Vibe Coding

I’m a U.Okay.-trained major college trainer with 11 years of expertise in worldwide colleges throughout the Center East and Southeast Asia. Through the years, I’ve seen librarians rigorously curate books solely to have them sit untouched on library cabinets. It’s because there was no systematic technique to join every youngster to the e-book most definitely to excite them.

Current options have been costly, inflexible, and constructed round proprietary e-book lists that didn’t match our assortment. The extra I checked out what was accessible, the extra I spotted the issue wasn’t that the expertise didn’t exist — it was that no person had constructed it for academics like me, working in colleges like mine.

So, I made a decision to construct one myself, utilizing an AI approach that I had examine with growing curiosity: vibe coding.

Studying to Construct an App

Vibe coding is a apply the place individuals use AI instruments to generate software program code by describing what they need in plain language to the device, with little to no conventional programming data required. So, I began vibe coding and telling a big language mannequin what I used to be making an attempt to construct. 

Progress was painfully sluggish — a day ahead, three days again. Over the summer time months I almost stop a number of occasions. The early structure choices haunted me: I used to be engaged on a 12-year-old Mac I hadn’t upgraded, and simply getting the appropriate improvement setting put in felt like a full-time job. The worst second got here when a number of recordsdata of code have been deleted with no backup. Hours of labor, gone. I sat staring on the display screen for a very long time.

Some of the painstaking phases concerned e-book cowl photographs — I needed to show covers for our library’s 10,000 books utilizing freely accessible API calls, with out scraping the data, to remain on the appropriate facet of copyright legal guidelines. Writing the code for this was exhausting. When it lastly labored imperfectly, I constructed a separate web page to manually consider each cowl — AI trying to find those that hadn’t loaded appropriately. That course of took weeks. Then the web page itself failed fully, and I needed to begin from scratch.

Switching from Copilot to Claude made a major distinction. It was nonetheless liable to errors and loops that might, as I put it to colleagues, drive me completely loopy. However it was extra dependable than what I’d had earlier than. 

What strikes me now could be how a lot has modified — what took me days and weeks in late 2025, I can now accomplish in hours. The speed of enchancment in LLMs is frankly horrifying.

How It Works

In the event you’re concerned with constructing the same device, the steps are easy: A trainer uploads their college’s library catalog as a CSV file — no re-cataloging required. The trainer then creates pupil profiles and runs a brief studying evaluation to gauge their studying stage and pursuits. The AI analyzes the catalog towards every pupil’s studying stage, pursuits, favourite authors and curriculum matters, and generates a customized studying record from the books already on the cabinets.

Pupil profiles embody identify, studying age, studying pursuits, favourite authors, most well-liked genres, and present class subject. These profiles energy the AI suggestions. Progress information consists of books learn, evaluations written, factors earned, and comprehension quiz scores. Pupil profiles and progress information are solely seen to their class trainer and college librarian — to not different college students.

When college students log in, they see their suggestions — sometimes 50 books ranked by how nicely the books match their profile. College students can mark books as “studying,” “completed,” or “wish to learn.” Once they end a e-book, they write a teacher-verified evaluate and reply AI-generated studying comprehension questions. Right solutions earn genre-specific factors which unlock equipment for his or her animated worm companion — one accent class per style throughout 21 genres, so studying extensively is rewarded, not simply studying so much. Pupil evaluations are fed again into the advice engine — so a hidden gem that one youngster discovers turns into seen to the entire college group over time.

The advice engine within the app attracts on a “grasp books” record I constructed from greater than 1,000 award-winning and extremely rated kids’s titles throughout varied classes. It’s not simply matching studying ranges — it’s actively surfacing books that the majority kids would by no means come across independently.

Generally a suggestion labored as a result of it was an award-winning e-book the kid had by no means heard of. Generally it was merely a style they hadn’t tried earlier than however which sat underneath a subject they’d listed as an curiosity — opening their eyes to a brand new nook of the library. Different occasions it was a pure subsequent step: the same creator, a continuation of a sequence, a e-book that constructed on one thing they’d already liked and rated.

For information safety, LibraryAid is COPPA and GDPR compliant. Pupil information is saved securely in Google Firebase. No pupil e-mail addresses are collected — college students log in by way of a school-issued code and PIN, with no private e-mail required. Information isn’t bought or shared with third events.

Constructive Suggestions From Colleagues and Household

Early on I informed a colleague what I used to be making an attempt to do. What she mentioned, and the sincerity with which she mentioned it, gave me extra confidence than any tutorial or documentation. She mentioned she genuinely believed I might make it work, and that I mustn’t surrender. Suggestions from different academics proved equally invaluable. It was frank and infrequently humbling. To this point, one colleague has built-in the app into her class and located it very helpful.

My 12-year-old son, nevertheless, grew to become maybe my most enthusiastic supporter. He spent appreciable time testing the system, informed his personal college about it and, in what felt like a distinctly up to date parenting second, informed me he’d requested an LLM whether or not LibraryAid had a excessive likelihood of being profitable and it responded with an enthusiastic “sure.”

What My College students Thought

When my device went dwell with my college students, one thing shifted in them. Youngsters who had been unenthused in regards to the library earlier than abruptly grew to become excited to discover it. Discovering their beneficial e-book grew to become a treasure hunt. College students started venturing into new sequence and authors they might by no means have chosen independently.

One pupil, an English learner studying roughly two grade ranges beneath his present placement, made 3x the common studying progress of his classmates as soon as he was matched to books that genuinely him on the proper stage. The expertise didn’t repair his studying struggles, nevertheless it  linked him to books well worth the effort of studying.

I additionally learn aloud to my class, ending the college 12 months with “Swimming In opposition to the Storm” by Jess Butterworth, which has a robust environmental theme. The affect of studying that e-book final 12 months was placing: abruptly the vast majority of the category was looking the app for journey tales with the same really feel. That second strengthened one thing I consider deeply in regards to the app — it really works finest alongside human affect, not as a substitute of it. The app surfaces the appropriate books for college kids, however the trainer or librarian sparks the curiosity.

What Vibe Coding Taught Me

Debugging code and diagnosing why a pupil isn’t understanding an idea require surprisingly related considering. For each, it is advisable be systematic, affected person, and hypothesis-driven. Writing algorithms that adapt to completely different studying patterns made me assume extra clearly about differentiation. And spending months constructing one thing that actual kids would use day-after-day gave me readability into why a lot edtech misses the mark. Not less than in my very own expertise, most training expertise is constructed for directors, not academics. It optimizes for reporting and information dashboards relatively than the day by day actuality of 30 kids with 30 completely different relationships with studying. The merchandise that work are those constructed by individuals who have stood in a classroom and felt the hole between what exists and what’s wanted.

Though my device surfaces an array of engaging books for youngsters, there is no such thing as a assure the suggestions will encourage them to take motion. I keep in mind a second I had with one youngster this time period, who confirmed me her curated record with a misplaced expression and eyes that have been pleading for steerage. Her record had hidden gems and well-known classics, all with interesting covers — some in her consolation zone and a few designed to stretch her considering. Nevertheless, the one one which her was a well-known sequence she already knew. The algorithm had performed its job. What she wanted subsequent was a dialog with a trusted grownup.

There isn’t a suggestion engine on the planet that may exchange the second a baby says, “I’m unsure about any of those,” and appears to their trainer or librarian for a nudge. The belief a baby has for the particular person standing in entrance of them can’t be coded.

My recommendation to any educator contemplating constructing their very own edtech device: construct one thing that extends what academics do relatively than replaces what they do. The expertise ought to deal with the matching however let the youngsters’s studying guides deal with the second.

LibraryAid has turned out to be probably the most helpful factor I’ve ever constructed, maybe even eclipsing a few of my classes.