Learn alone. Talk together.

The Majamaja Method

Learn Alone, Talk Together. You study on your own with step-by-step lessons, then use what you learned in real conversations with AI friends. Each step is built on learning principles that research has studied for decades.

  1. Review right before you forget

    Spaced repetition: words come back after 1, 3, 7, 14 and 30 days.

    Many studies show that spreading practice out over time helps you remember longer than cramming, including in foreign-language learning. [1][2]

    Majamaja — Review cards on your home screen, plus optional extra words after each lesson.

  2. Pull it out of your head

    Retrieval practice: you rebuild sentences, fill blanks, write what you hear and rewrite sentences yourself.

    Meta-analyses find that recalling something on your own is more effective than reading it again. [3][4]

    Majamaja — Every lesson has recall, sentence building, blanks, dictation and listening without text.

  3. A hint first, not the answer

    When you make a mistake, Han-ssaem first gives a hint so you can fix it yourself. The answer comes only if you need it.

    Classroom research found that prompts that push learners to correct themselves work better than simply restating the answer. A 2025 study found that AI that just gives answers can hurt learning, while AI that gives hints largely avoids that harm. [5][6]

    Majamaja — Hint → fix it with blocks or by typing → answer and reason in your language. Your mistakes become review cards.

  4. Talk to get something done

    Every lesson ends with a mission conversation with an AI friend: order a coffee, open a bank account, give an opinion at a meeting.

    Task-based teaching and speaking practice show positive effects in research reviews, and recent meta-analyses report moderate gains from practicing with AI conversation partners. [7][8]

    Majamaja — Nari, Taeo, Grandma Suni and others remember you and move the mission forward step by step.

  5. Learn speech levels on purpose

    You see who speaks to whom and how: polite, formal, or casual, with the same sentence in all three.

    Research reviews find that pragmatics, such as politeness, can be taught, with explicit explanation tending to help. Even advanced learners of Korean find honorifics hard. [9][10]

    Majamaja — The speech-level navigator, the 'shall we talk casually?' moment, and politeness tips from Han-ssaem.

  6. Explanations in your language

    Grammar notes, hints and translations come in English, Spanish, Vietnamese or Japanese.

    A meta-analysis found that glosses in the learner's first language help more than glosses in the target language, especially for beginners. [11]

    Majamaja — Your language at every step, while the Korean stays on screen and in your ears.

The studies below are other researchers' work, not tests of Majamaja itself. We will publish our own learners' results, with sample sizes and limits, after launch.

Chat with Nari

References

  1. Cepeda, Pashler, Vul, Wixted & Rohrer (2006). Distributed practice in verbal recall tasks. Psychological Bulletin. doi.org/10.1037/0033-2909.132.3.354
  2. Kim & Webb (2022). The effects of spaced practice on second language learning: A meta-analysis. Language Learning. doi.org/10.1111/lang.12479
  3. Rowland (2014). The effect of testing versus restudy on retention: A meta-analytic review. Psychological Bulletin. doi.org/10.1037/a0037559
  4. Adesope, Trevisan & Sundararajan (2017). Rethinking the use of tests: A meta-analysis of practice testing. Review of Educational Research. doi.org/10.3102/0034654316689306
  5. Lyster & Saito (2010). Oral feedback in classroom SLA: A meta-analysis. Studies in Second Language Acquisition. doi.org/10.1017/S0272263109990520
  6. Bastani, Bastani, Sungu, Ge et al. (2025). Generative AI without guardrails can harm learning. PNAS. doi.org/10.1073/pnas.2422633122
  7. Bryfonski & McKay (2019). TBLT implementation and evaluation: A meta-analysis. Language Teaching Research. doi.org/10.1177/1362168817744389
  8. Lyu, Lai & Guo (2024). Effectiveness of chatbots in improving language learning: A meta-analysis. International Journal of Applied Linguistics. doi.org/10.1111/ijal.12668
  9. Taguchi (2015). Instructed pragmatics at a glance. Language Teaching. doi.org/10.1017/S0261444814000263
  10. Brown (2011). Korean Honorifics and Politeness in Second Language Learning. John Benjamins. doi.org/10.1075/pbns.206
  11. Kim, Lee & Lee (2020). The relative effects of L1 and L2 glosses on L2 learning: A meta-analysis. Language Teaching Research. doi.org/10.1177/1362168820981394