stardance has been extended another month! the new deadline is october 31 :)

You are browsing as a guest. Sign up (or log in) to start making projects!

SolariStudy

  • 5 Devlogs
  • 18 Total hours

AI models evolved, study tools didn’t. SolariStudy solves that.

Ship #1 Changes requested

Hi! I created SolariStudy, basically a specialised study platform and productivity app (I built it with React Native, Expo and Supabase). The app addreses a problem which I face a lot every day and a lot of students preparing for rigorous exams and olympiads face it too: standard AI tools tipically just generate big quizzes in a MCQ format or just give immediate solutions that kind of ruin the learning process (also cluttering interfaces with unorganized chat logs). My idea for this app was to try a dual-mode engine which features SolariLearn for normal tutoring (just perfect for going through study materials or books) and SolariSolve for strict, timed problem sessions (very useful for Olympiad preparation especially).
Here I introduced major QoL improvements that structure the revision workflow, including organizing sessions into dedicated, isolated subject folders (like Mathematics, Physics, Linguistics, Astronomy etc.) to prevent the cluttering of chats (one of the problems mentioned earlier, which is solved by a few AI’s, but the process of organizing is not automated). The app also implements automated worksheet ingestion to extract and prepare textbook problems, introducing exam focus sprint timers to enforce accountability. By using the SolariSolve mode, you are able to get step-by-step scorecards with streak and accuracy tracking.
The most challenging tech hurdle was engineering the streaming AI pipeline (faced a lot of bugs here and did not really know where to start from), but also mathematical rendering ragebaited me at the end… Resolving API dropouts and rate limits required me to implement an exponential backoff with a dynamic model fallback system, alongside the real-time latex rendering to display the math formulas (which were essential for physics, math and astronomy so I couldnt just use normal text).
I am proudest of turning this small concept into a functional , working cross-platform project that I feel balances an unstimulating focus environment with rigorous grading (which is objectively done by the AI tool).
Now, for testing, you should know that while a compiled Android APK is abvailable for mobile testing, running the web version locally on pc is kinda my own recommendation :) since the mobile part was more of an experimental preview which can still receive UI polishing in the future. Most of the instructions are in the READme, but I can paste them here again. Local setup required node.js, cloning the repository, running npm install, supplying supabase and gemini api keys in an .env file and launching the project by entering in terminal npx expo start -w to test the engine directly in a web browser.
I really hope you like this project and that you can maybe use it for your own personal use.

Try project → See source code →
Open comments for this post

1h 46m 14s logged

5th and last SolariStudy devlog - This was it… finally over. Even though I thought I was close to finishing 2 days ago, I faced a serious bug with latex rendering, also found out that the AI model I was using in the code was 3.5-flash instead of 3.5-flash-lite which is very limited in terms of number of messages so I was hitting rate limits on the app a lot. Thankfully I made it out through them and also made a READme with some help from a github readme which I found (i credited him in my github READme). You can guys actually try my app. (I tried to do as much as I could, but the lack of tutorials online made the Android version of the app being partially functional, you can test it and return to me with some bugs, but it will be quite hard to fix them, so for the moment I will go with the fully functional web app). Thank you for all the attention and support, and let’s go on with the next project!

0
0
43
Open comments for this post

2h 4m 16s logged

4th SolariStudy devlog - Here we are with the completed project I can say (everything that is left to do is just some app icons, maybe touch up on some things related to the design andd the readme, of course). What I’m most proud of is that the app finally works on android, and it can be downloaded (I’ll prolly put the link/qr code in the readme). It’s been a long journey, but I am really happy of what I achieved here and maybe the app can be even launched publicly on appstore one day. See you tomorrow guys :smil:

1
0
41
Open comments for this post

2h 40m 41s logged

3rd SolariStudy devlog - Again a long week has passed and school kind of made me lose a lot of precious time. Although here we are anhd lemme tell you what I’ve done this week: - I added a stale-while-revalidate caching pattern for study folder, sessions and global leaderboards so that reads work seamlessly without internet, then I built a write-side mutation queue to capture offline actions (like creating folders, updating timer solve stages and logging session details), also integrated a bg network listener to automatically detect reconnects and flush the queued mutations back to supabase. After working on this I though it would be nice to stabilize the end-to-end chat and polish the study session lifecycle. Also worked a little on the security of the app. I hope to do more these couple of days and maybe get closer to launching this app :) Cya in the next devlog guys

0
0
123
Open comments for this post

7h 44m 3s logged

2nd SolariStudy devlog - Hellooo, I believe a week passed since my last devlog on this project… uhm yeah also the time logged is way longer than usual since I tried to do as much as possible to make the app functional. I will say some things about what I added in the meantime. I replaced all the placeholders with real , live data (also added a custom postgresql function that aggregates score dynamically across chat sessions and messages without duplicates), I wrote some trigers that automatically calculate the total problems solved and accuracy percentages whenever a study session finishes or a message is graded, ran a migration and onetime backfill query so that historical data stays in sync. I finished the architecture in db.ts, where I have now folder nesting, scoped session filtering, message grading accuracy toggles, global search and daily activity streak. (I want to say this is the first time I felt like giving up on a project (ok I know it is just my 2nd project, but I feel its kind of a serious step from my 1st one). I learned a lot like writing functions in sql editor (using supabase), using react native state and doing the UI sync, making the AI worflow and many others. It really was a lot but thankfully I got through the most of it. Sadly I also get the same problem as for the last project, because I plan my code beforehand, the time registered I feel doesn’t reflect at all my work on this project. I think I spent over 30h brainstorming, learning and planning the code, only for around 10h to be logged in which is basically the hard coding time. Well, either way, my main goal is to make the most out of this project, not log as much time as possible, however it would’ve been nice to see exactly how much effort was put into this). There is a lot more to do like a lot of testing to see if the app can be improved, to touch up on some things and maybe then I can present the finished app soon. Cya in the next devlog :smile-wx:

2
0
105
Open comments for this post

3h 22m 28s logged

1st SolariStudy devlog - Here is my new project, a project meant to be a better study app. Current AI tools for studying are pretty boring and have very few functions. Topics like mathematics and physics can’t be learned by memorizing or taking quizzes, but by solving as many problems as possible. After more than 3h of trial and error I think I got an UI that I like (i found it on dribbble) and planned a few of the functions I want to add onto the site. I am very open to suggestions/ideas if you have some, or even a like :). (If you wanna continue reading, here are some things I wanna say: first, I finally returned to stardance. I was quite busy with personal study and activities and I sadly neglected this activity. However, I am eager to finish this project and start a few more to reach some stardust goals (like the small shark :) ). secondly, the current site is just frontend, no backend made yet and for that reason i added placeholders to have an idea of how everything would look on the site. third, I really appreciate your guys support from the personal site project and together with you I can maybe ship and pursue more projects in this amazing first hackathon for me). Here are some photos:

0
0
143

Delete project?

Are you sure you want to permanently delete this project? This action cannot be undone.

All devlogs, followers, and associated data will be removed.

Followers

Loading…