Bloom

Bloom is an AI-powered private tutor that provides one-on-one tutoring based on Bloom's 2-Sigma research. It generates a structured syllabus, delivers adaptive lessons, reads your annotations and feedback, and tailors the next lesson to your understanding level — just like a real tutor would.

Use Cases

• Anyone who wants to learn any topic
• Supports three modes: enter a topic, upload a source file (PDF/TXT/MD), or upload project files
• Ideal for learners who want adaptive pacing and personalized feedback

Preview

Core Capabilities

• Three course modes — generate from a topic, upload a PDF/TXT/MD source, or Project Files (upload files/folder, render each directly, highlight-ask anytime, no syllabus or next-lesson generation)
• Learning depth — choose simple, standard, or deep syllabus expansion when creating a course; shown as a badge on each course card
• Reference material — paste textbook chapters, papers, or notes when creating a topic course
• Next-topic recommendations — generate 3 course-ready topics from your full learning history, refresh the set, save ideas to a learning queue, or start one directly
• Highlight Q&A sessions — select any text in any lesson (or source) and a small icon pops up; click it to ask. The highlighted text stays marked in yellow, the AI answers instantly, and you can keep asking follow-ups. The window is draggable and collapses into a margin dot you can reopen anytime.
• Adaptive lessons — each lesson addresses your specific gaps from the previous one
• Chapter sidebar — quick-jump between lessons while reading
• Collapsible syllabus — track mastery progress without clutter
• Streaming generation — watch AI write the next lesson in real-time
• Personal center & learning calendar — open the profile from the header to see a month calendar shaded by daily activity; click any day to see which courses, lessons, and highlights you studied, alongside overview stat cards and a six-month contribution heatmap

How It Works

Topic Mode

1. Create course → AI generates syllabus + lesson 01
2. Read lesson → highlight text → add annotations
3. Write feedback → answer thought questions
4. Click "Done Reading" → AI generates next lesson (answer review + annotation responses + new content)
5. Repeat until all mastery items checked ✅
6. Auto-generate evaluation → then summary

Source Mode

1. Upload PDF / TXT / MD → AI generates syllabus + source-reading chapter
2. Read source → highlight text → ask and get an immediate answer
3. Click "Done Reading" → AI reads the full source + Q&A, then generates the next lesson
4. Continue with the normal adaptive lesson flow

Project Files

1. Upload a file / multiple files / a whole folder → each file renders directly as one page
2. Read each file → highlight text → ask and get an immediate answer
3. No syllabus, no next-lesson generation; the files and highlight Q&A feed next-step recommendations

What You Need to Provide

Web Mode

• Python 3.11+ and Node.js 18+
• An OpenAI-compatible LLM API key (e.g. DashScope, OpenAI, etc.)
• Configure the LLM_API_KEY in a .env file

CLI Mode

• Claude Code
• The bloom-tutor skill added to Claude Code

What You Get

• A complete personalized course (syllabus + multiple lessons)
• Adaptive learning experience: each lesson adjusts based on your feedback
• Highlight Q&A sessions with instant AI answers
• Course evaluation and summary
• Next-topic recommendations to continue learning

Usage Examples

• Web mode: Open the website, click "New Course", choose "Topic", enter "Python basics", set learning depth, and start learning.
• CLI mode: In Claude Code, say "Create a new folder and help me learn [any topic]".

How to Choose

Both follow the same flow: syllabus → lesson → annotate → feedback → next lesson → evaluation → summary.

Portable Claude Code Skills

Bloom ships a set of portable Claude Code skills. Each skill is self-contained and can be used after copying it into a skills directory.

The Science

Notes

• Web mode requires a valid OpenAI-compatible API key. Ensure it is correctly configured in the .env file.
• CLI mode requires Claude Code and proper skill directory setup.
• Project Files mode does not generate a syllabus or subsequent lessons; it is only for reading and asking questions.
• All data is processed locally; AI calls are made through your own API key.
• Course content is entirely AI-generated. Users should verify information accuracy based on their own judgment.