I made my AI tutor stricter: no next lesson until you pass 80%

A developer has built LearnOptima, an AI tutoring product from Valynx, that gates each day of a generated 30-day or 100-day learning plan behind an 80% quiz score, blocking access to the next lesson until the threshold is met. The system routes grading and logic validation to GPT-OSS 120B and high-volume lesson content and tutoring to DeepSeek V4 Flash via OpenRouter, on the principle of spending reasoning where mistakes are costly and saving cost where volume is high. The developer cites a preliminary study suggesting recall tests outperform repeated rewatching for week-later retention, while noting the evidence is mixed.

published: True Most learning apps remove friction. We added some. In LearnOptima, a product from Valynx, the company I founded, you can't open the next day of your plan until you score 80% on today's quiz. Here's the reasoning, how it's built, and what I don't know yet. A video course is a library. Everything you need is in there, and nothing tells you what to do tonight. Anyone who has started one knows the day it stalls: you're tired, the next lesson is long, and "tomorrow" wins. A plan is different. It says exactly what today is, and it's small enough to finish. In a preliminary study using a recorded Coursera lecture, people who rewatched it four times did better on a test five minutes later. A week later, the people who watched it once and took recall tests did better. Other studies are mixed, so I treat it as a hint, not a rule. It still shaped the design: every day ends with a quiz, not another rewatch. You give LearnOptima a skill, your experience level and how much time you have each day. It generates a 30-day plan for you, fresh each time and not a static template. A 100-day Mastery plan is also available. Each day has the same shape: The gate is one rule: js const PASS MARK = 0.8; function canUnlockNextDay correct: number, total: number : boolean { return correct / total = PASS MARK; } That's a simplified version, but the rule really is that simple. No pass, no next day. LearnOptima routes work through OpenRouter: | Job | Model | Why | |---|---|---| | Logic validation and exercise grading | GPT-OSS 120B | wrong judgments do the most damage here, so it gets the heavier reasoning model | | Lesson content and tutoring | DeepSeek V4 Flash | high volume, so speed and cost matter more | The rule of thumb: spend reasoning where a mistake hurts, and save money where volume is high. How do you stop LLM graders from drifting on open-ended exercises? If you want to try it, the first plan is free: learnoptima.online https://learnoptima.online