I Canceled My French Tutor and Built an LLM Tool That Does It Better
Alex Shelaev
SubscribeSign in
I Canceled My French Tutor and Built an LLM Tool That Does It Better<br>It costs me just several dollars a month, and I remember what I learned much better. Here's what I built and how.
Alex Shelaev<br>Jun 21, 2026
Share
Several months ago I was doing French lessons the old school way — a 45-minute lesson with a private tutor once a week, for $200 per month. The tutor had a solid academic background, a sound methodology and was a nice person to interact with. But several months in, I started realizing that we were covering a lot of topics, but I wasn’t retaining them all that well — even given that we were repeating them from time to time.<br>Every session, we’d spend the first 20 minutes conversing, then a lot of time covering the topics we’d already covered, since many of the topics were complex and required a lot of repetition. As a result, the progress to new grammar topics was pretty slow, and I was getting impatient.<br>I’d read enough about the forgetting curve to understand where the challenge was coming from, and I’d been tinkering with LLM tools for a while, so I started wondering: could I build something that did this better — and cheaper?
The actual problem I was trying to solve
The gap in my tutoring setup wasn’t the quality of the instruction. It was two structural things.<br>First, the review cadence. Human tutors schedule by calendar. The algorithm I needed schedules by forgetting curve — reviewing each topic right before I’d lose it, not at random times later. This is called spaced repetition, and there’s 40 years of memory research behind it. Apps like Anki have proven it works. The question was how to apply it to something more nuanced than flashcards, which I tried before and never liked.<br>Second, the error tracking. My tutor remembered, broadly, what I found hard and tested me on that periodically. But “Alex struggles with subjunctive” is not a very useful data point. What I actually needed was more along the lines of: “Alex consistently uses avoir as the auxiliary for aller in passé composé when the sentence is negative.” That’s what would have made it much more precise and help resolve the challenge faster.<br>And finally, did I really have to pay for just conversing for the first 20 minutes, and do that just once a week? What if I could practice my spoken French anytime I wanted and for free or at a minimal cost?<br>All of that felt like solvable software problems.
What I built
Two key components (grammar and speech practice), designed to work together.<br>The knowledge base tutor is a text-based workflow built on Claude. It manages a JSON file that tracks every grammar topic I’ve studied — when it was last reviewed, how confident I was, what specifically went wrong, when it’s due again. Before each session, it reads that file, identifies what’s due for review, and generates exercises in escalating difficulty: multiple choice first, then fill-in-the-blank, then translation, then free production. After the session, it writes everything back to the file.<br>I can also give it screenshots of any study book I’m working through and do exercises on that material, or ask any grammatical question I may encounter elsewhere. All this gets added to the knowledge base.<br>The algorithm underneath it is SM-2 — the same one Anki uses. After each topic, I rate my recall 1 to 4. That rating adjusts two things: the ease factor (how naturally this topic sticks for me specifically) and the interval before the next review. Nail something four times in a row and it comes back in three weeks. Blank on it and it comes back tomorrow. Over time, it helps the system to develop a pretty accurate model of my personal forgetting curve, topic by topic.<br>The weak-spot tracking is geniunely useful. Rather than logging “Alex has trouble with passé composé,” it logs “uses wrong auxiliary with motion verbs when sentence is negative — since 2026-04-12.” The next session that topic comes up, the exercise is built around exactly that construction. Not a general passé composé drill — the specific thing that broke.<br>I initially tracked every session separately but eventually decided to only keep the latest snapshot of my overall knowledge state, since the JSON was getting too long. It may still get too long even as a single snapshot eventually, and I may need to split it into several files in the future.<br>The speech tutor (called Causons). It’s a browser app where you can click the mic button, speak in a language of your choice and hear the response in the same language. It reads the same knowledge base at the start of each session and steers the conversation toward due topics and known weak spots. It also corrects genuine grammar errors, inline, in the flow of conversation. Not every error — only things that are objectively wrong, things a native speaker would never say. Transcription artifacts, punctuation, register choices, colloquial...