docs: Add Competitor Analysis doc#27
Conversation
cboiteux2765
left a comment
cboiteux2765
left a comment
There was a problem hiding this comment.
Looks good, I just left comments as questions or pointers but very thorough
|
|
||
| Uses OCR and AI to generate study materials | ||
| #### Competitors | ||
| - **FlashRecall** - generates flashcards from any study material & has SRS |
There was a problem hiding this comment.
So this assumes that someone is in a class and is more of an AI language tutor? If we're talking general public they won't have study material so that's an advantage for us, because our system can make the study material for them
| - **NewWord** - AI-powered multilingual vocabulary notebook | ||
| - AI generates definitions from typed words or OCR | ||
| - Photo OCR to scan words from textbooks | ||
| - Can translate words into multiple languages simultaneously |
There was a problem hiding this comment.
When would be a use case for this? And is it counter-productive to learn multiple languages at once?
| - Photo OCR to scan words from textbooks | ||
| - Can translate words into multiple languages simultaneously | ||
| - Spaced repetition review system | ||
| - **AlgoApp** - General flashcard app with AI features |
There was a problem hiding this comment.
So it's just a "formatter" pretty much with SRS, but our system is formatting and understanding, we treat our system as an expert so it doesn't need input items like the others
| #### Cons | ||
| - FlashRecall & Laxu AI : Not language-specific | ||
| - NewWord: Shallow content (just definitions, no examples or patterns) | ||
| - AlgoApp: Android app has major bugs, expensive, no LLM Q&A |
There was a problem hiding this comment.
Something to also consider is that we can serve a cross-platform website + mobile view but if we really care about latency then you'd need to write it in each phone's native OS (Swift for iOS and Kotlin for Android). But for now the latency is assumed to happen since it's an LLM
| - Uses markdown (like Obsidian) -- flexibility in formatting & converts to many other formats quickly | ||
| - Much better UI than Anki's | ||
| - Has dashboard of user's learning stats & activity (like GitHub's) | ||
| - Can create knowledge graph (like Obsidian) -- see relationships between cards |
There was a problem hiding this comment.
Could be a v2 thing where we link relationships between cards
| - Has dashboard of user's learning stats & activity (like GitHub's) | ||
| - Can create knowledge graph (like Obsidian) -- see relationships between cards | ||
| - Can create "note" cards too (single-sided) | ||
| - Built-in language tools: dictionary lookup, translation, text-to-speech |
There was a problem hiding this comment.
Even though we said text-to-speech is a v2 thing I think it's pretty important to consider since people can't be typing all the time, and if people are trying to find the meaning of a word they don't know it's easier to sound it out than type it
| - FSRS is bad -- only have "remember / forgot" options for spaced repetition | ||
| - Uses markdown -- can be a learning curve for those that aren't familiar with it | ||
| - Limited export features | ||
| - Desktop app is free, but must subscribe for syncing features -- aka must pay for sync to mobile ($5/month) |
|
|
||
| #### Kitsun.io - Japanese SRS with reading integration (Closest competitor for Japanese) | ||
|
|
||
| **Pricing**: $5/month or $160 lifetime |
There was a problem hiding this comment.
Since this has no AI and basic stuff it sounds pretty hard-coded
2 participants
Description
Related issue(s)
Closes: #21