Launching Hurroz

Two Opus 4.7 sessions open, two projects in motion — that's been my rhythm lately. Most of the day belonged to the regular work, the kind that pays the bills. But Hurroz, my personal venture, phase 1 is already finishing up. Yesterday it was almost there. All that remained were the small things — minor UI edits, a few Flutter warnings nagging from the corners, an unused variable here, a context error there. Nothing dramatic. It all came together quietly, and as I write this, the app is making its way up to the Play Store. Fingers crossed.

The new design is striking, maybe even a little bold for a journaling app. Whenever I sit down to generate code with Opus 4.7, it wants to talk first — questions, then more questions, and somewhere along the way the whole afternoon is gone, spent explaining the vision. The AI has grown slower in its execution, even as the results have grown sharper. I keep thinking — enough with the questions. So I ran a small experiment: I stopped pushing back and simply accepted whatever defaults it recommended. To my surprise, it worked. The feature came out perfectly. But here's the catch — Claude can write code, but it cannot design. The UI it produces is cluttered, dense, and clearing it up takes ages.

Gemini is the opposite. It has a real eye for design, but carrying code from one chat into another is always a coin toss with it. So I've settled into a workflow that suits me: build the feature first, get it working, then hand the visual direction over later. People sometimes ask why I don't design the UI before writing the code. Honestly, I believe an architecture-led UX serves the end user better. Once the bones of a feature are working, that's when the real design begins — moving things around, finding the rhythm, letting the screen breathe.

Supabase has made all of this gentler. Compared to projects where I had to build out a whole Python backend from scratch, this feels almost like a relief. I find I enjoy the front-end work more anyway. Though I'll admit — Streamlit in Python still has a way of turning out the most beautiful tables.

By the time I finished writing this journal, the app went live.

Last 10 days were very significant for me. Both on personal front and in business.

I explored Sol and realized that self discovery is hard. It asks those questions which a normal claude or gemini or chat gpt won't. It make me go deeper. I even got frustrated so many times when it reviewed that my thoughts were not deep enough. It kept asking me for real examples.

And when I provided those examples, it kept asking me how I felt. He wanted to know my reactions. And every time it made me so raw and emotional that just I didn't speak to anyone for a short while. It took me time to compose myself.

I am not sure what others would feel. But I definitely know that they will be frustrated. It is only after they leave their frustration aside, can one truly go deeper. I can change settings so it doesn't ask us to go that deep but i don't really want to. Current settings are set at 7 out of 10 which is quite decent. Reaching seven wasn't easy for me.

The first thing I wrote, I got 3.5. That was just shocking. But Sol wants things too personal. And sometimes, I think, whether I should share so much with an AI.

I haven't added any memory and past chat searches. If I do, I know, if I am ready for that. I mean I wouldn't want to talk about something that I discussed 2 months back. Some memories are good but some are painful. The best way to deal with them is to deal with them when you are ready. And how do you get ready by writing down your current experiences. I don't need no one give me cues and ideas when I am in an emotional state. What do you think

Anyway, I did finish google sign in on Android Play Store. That simple thing took so much time because I used the SHA1 key in another project, that I couldn't find. You got to be careful with the these keys and I learned it the hard way.

I also worked on Hurroz Law which was a new learning curve. Dealing with so much data is experience in itself. Now I know why data analytics is a tricky thing. You have to ensure all the data is aligned and normalized. I mean come on. .. what is normalization. It is most unnormal thing. Ensuring Saurav Ganguli and Mr. Saurav GAnguli and MrSaurav Ganguly are the same. That is normalization. That is not fun but overall a good experience.