What you get
Where you highlight and what you ask shapes how the next lesson gets written.
Bloom: Chasing the One-to-One Tutoring Effect
Added 2026-08-06The basis is the 1984 two-sigma problem — students given one-to-one tutoring scored two standard deviations above a conventional class, into the top two percent. Note this is not Bloom's taxonomy.
The loop is fixed: outline, lesson, annotation, feedback, next lesson, assessment, summary; once every mastery item is covered, assessment and summary generate themselves. Inline questioning is distinctive: select text, an icon appears, the passage stays highlighted, and each conversation's context is the whole lesson, the highlighted passage and that conversation — and your questions feed into how the next lesson is written. The web mode is self-hosted with your own model key; the CLI mode needs only Claude Code.