August 11, 2026

LLM Tools|Index 04

Keet Generates Custom Learning Courses with AI-Powered Video and Games

A new mobile application, Keet, leverages AI to create tailored educational courses on any topic, integrating short video explanations and interactive assessments to provide structured self-paced learning.

Via
AITECH TOKYO Editors
Dateline
Tokyo, August 11, 2026
Date
August 11, 2026
Time
6 min read
Keet Generates Custom Learning Courses with AI-Powered Video and Games

Tagline

Custom learning paths with AI-generated videos and games.

Who & Why

For a Tokyo-based professional seeking to quickly understand a niche or complex topic for a new project, Keet could provide a structured curriculum complete with explanations and assessments, saving research time.

vs. Existing

Unlike existing platforms like Coursera or Udemy which offer predefined courses, or YouTube/ChatGPT which provide unstructured content, Keet aims to generate a tailored, curriculum-like experience on demand, integrating videos and interactive elements.

Tokyo Take

Keet offers an interesting approach to personalized learning, but its current beta status and lack of explicit Japanese language support or localized content mean it holds little immediate practical value for Tokyo professionals. The slow generation time also limits its utility for urgent, on-demand learning needs common in fast-paced Tokyo business environments.

Keet is a mobile application designed to generate customized educational courses on demand, featuring short video explanations and interactive games for reinforcement.

Developed by co-founders Zack and Tommy, the app aims to replicate a structured curriculum experience for self-learners. It addresses the common challenge of fragmented learning by sequencing lessons logically and finding appropriate starting points based on user input.

Users specify desired difficulty, depth, and learning intent. Keet then categorizes the topic using Biglan categories (Hard–Pure, Hard-Applied, Soft–Pure, Soft-Applied) to tailor instructional approaches. For example, a "hard-pure" course might emphasize worked problems, while a "soft-pure" course would use primary source narratives.

The platform distinguishes itself through its multimedia approach. Explainer videos are produced using specialized tools: Manim for mathematical visualizations and Remotion for animating processes or presenting primary source material, akin to Vox-style educational content. The founders noted that "Vox and 3B1B videos made complex ideas accessible, which inspired us to move towards video based lessons."

Beyond passive video consumption, Keet incorporates custom activities for assessment, moving beyond traditional multiple-choice questions. A genetics course, for instance, might involve interacting with a DNA model to reinforce concepts.

Currently in TestFlight beta, Keet offers three free course generations. The founders acknowledge that personalization is still in early stages, with future plans to adapt more deeply to individual learner backgrounds and weak spots. Course generation is intentionally slow to prioritize quality.

The eventual business model will be a monthly subscription providing credits for course generation, similar to Suno. While the immediate impact for Tokyo professionals is limited due to its beta status and US-centric launch, its approach to structured, personalized learning could eventually simplify continuous professional development.

The Briefing

World AI tech, read from Tokyo. Once a week, in Japanese.

Each Friday: the five global AI tech stories Japanese business professionals should know about this week, translated and read through a Tokyo lens — what it means for Japan, what to act on, what to keep watching.

We respect your inbox. Unsubscribe anytime.