I started with a simple website scraper, but it quickly became clear that it only worked well for tech startups. So I pivoted hard: I added parallel sub-page fetching for contact and about pages, built Wikipedia integration to pull founding data, and spent a lot of time fighting ugly wikitext template parsing bugs. I also expanded industry detection from 5 categories to 20+, which made the scans much more accurate across different kinds of businesses.The UI got a full redesign too, from something vibecoded into something much more editorial, with a dark hero section, Cormorant Garamond serif text, and electric blue accents. The most important addition was the “Ask AI” button: Groq’s llama-3.3-70b now fills in missing founders, revenue, and key products on demand, but only when clicked, so there’s no latency penalty during normal scans. After setting GROQ_API_KEY on Vercel and deploying to production, the project became a full intelligence tool that can generate detailed reports for both Stripe and local businesses. Ship the thing.

got feedback that the readme sounded too AI-generated. stripped it down, rewrote it in first person, added a screenshot, trimmed features to 6 bullets. removed the corporate FAQ, the exhaustive tech stack list, everything that felt like a template. readme now sounds like i actually wrote it instead of a marketing team approving it. added a “how it works” section that tells the real build story instead of listing libraries. shipped it.

Devlog — Killed the Grok API Dependency

clarification questions were broken. Grok API wasn’t recognizing any model names (grok-2, grok-beta, grok — all failed). spent 15 minutes debugging dead ends.

gave up on the api. switched to hardcoded template questions instead. built question templates for each category: research gets different questions than business, different from writing, etc.

now when user hits execute → instant questions pop up → no api calls, no latency, no failures. just works.

same feature. actually reliable. 🚀

OneShot Dashboard Redesign

Spent the week tearing down the OneShot dashboard and rebuilding it with a clean black/white aesthetic. Text was disappearing, colors were fighting each other, and the whole thing felt half-baked.

Went through five pages and standardized the color system: solid white for primary text, opacity variants for secondary, and proper contrast everywhere. Same features, completely different vibe.

The real win? Design isn’t decoration. When a page is polished, users assume the engineering is solid. Now it actually looks like I care about the details.

Ship first, perfect later.

I improved the UI to make the project look more polished and intentional, with cleaner spacing, better visual hierarchy, and a smoother overall experience. I also rewrote the README so it felt more human and easier to understand, instead of sounding like a wall of technical notes. On top of that, I added a few new features that make the app feel more complete, more useful, and closer to something people would actually want to keep using.

I started with a simple website scraper, but it quickly became clear that it only worked well for tech startups. So I pivoted hard: I added parallel sub-page fetching for contact and about pages, built Wikipedia integration to pull founding data, and spent a lot of time fighting ugly wikitext template parsing bugs. I also expanded industry detection from 5 categories to 20+, which made the scans much more accurate across different kinds of businesses.

The UI got a full redesign too, from something vibecoded into something much more editorial, with a dark hero section, Cormorant Garamond serif text, and electric blue accents. The most important addition was the “Ask AI” button: Groq’s llama-3.3-70b now fills in missing founders, revenue, and key products on demand, but only when clicked, so there’s no latency penalty during normal scans. After setting GROQ_API_KEY on Vercel and deploying to production, the project became a full intelligence tool that can generate detailed reports for both Stripe and local businesses. Ship the thing.

built an AI execution engine. you describe what you need, it gives you professional results in seconds. rewrote the README to sound human (last one looked AI-generated). fixed UI readability, added progress bars, implemented retry logic for API stability. it’s live at oneshot-chi-nine.vercel.app and actually works. and my vercel kept deploying my old deployments so fixing that took me a long time i also added a progress bar feature so users dont get stuck on the screen showing nothing and yea some of the previous buttons weren’t working or were glitched so i fixed those too.

added supabase integration so tasks actually persist. implemented rate limiting (5 req/min per IP) to prevent abuse. built out an 8-template system with optimized prompts for common workflows (business plans, landing pages, marketing strategies, etc). added keyboard shortcuts (Cmd+K to open quick task search) because power users deserve fast access. implemented result modal for viewing full results without scrolling. settings now persist to localStorage so user preferences stick around. updated all dashboard pages to pull real data from the database instead of hardcoded samples. everything still works without a database configured, it just gracefully degrades.the app went from “works but doesn’t persist anything” to “production-grade SaaS with templates, shortcuts, and data persistence.” still under 10kb of production bundle js. no bloat. everything has a reason for existing.

spent the session debugging task execution flow - users were getting stuck on the “executing” page. turned out to be a routing issue after the api call completed. fixed the navigation and now tasks flow through smoothly from submission to results. also deployed the whole thing to vercel so it’s actually live and working with real results. copy and download buttons are fully functional. ready for people to start using it.

okay so we shipped the whole dashboard. like actually shipped it. all 7 pages, interactive examples modal, task execution timeline, templates, the whole thing. UI is clean and professional, no jank.built it on next.js 15, deployed on vercel, live right now at oneshot-chi-nine.vercel.app. github repo is up too: github.com/nadellasripad11/oneshot honestly the UI part was pretty smooth. typescript caught bugs, tailwind made styling easy. but the REAL challenge is gonna be the LLM integration. we’re thinking either open source models or building something lightweight since API costs would kill us.that’s basically it!!! everything works, it looks good, and we’re ready for the next phase. hope people actually use this lmao. thanks!!!!

I basically worked making the whole roadmap of the whole project. main components were the UI, systems and appealing to the customers. I also figured using API keys to make our prompts better would take too much money, so im gonna make my own LLM or use a free one. and that’s it thanks!!!!!! hope i got a lot of engagements on this

This session focused on polishing SerenityOS for production launch and fixing critical bugs that were blocking user-facing features. Started by diagnosing and fixing the messages system - the Contact form was saving messages to localStorage, but they weren’t displaying in the Messages app due to a DOM timing issue. Wrapped the contact handler in setTimeout to ensure proper initialization, and implemented a dynamic renderMessages() function that rebuilds the DOM on demand. Tested the full flow end-to-end: Contact form → localStorage → Messages app, confirming persistence and deletion both work. Next tackled calculator button overflow - buttons were massively oversized and breaking the window layout. Reduced padding from 10px to 6px, gap from 6px to 4px, and display font-size from 2em to 1.5em while adding min-width constraints. Buttons now fit perfectly within the window. Compacted the Projects app since it was taking up unnecessary vertical space - reduced font sizes, cut spacing between projects, and shortened descriptions so all five projects display without scrolling. Updated the README following professional shipping guidelines: punchy one-liner, prominent demo link, six specific features, technical depth explaining architecture, quick start in three lines, browser support, and creator info. No boilerplate or template text. Completely rewrote portfolio content across all apps (About, Projects, Portfolio) with real information: full bio, three-skill categories (technical, business, leadership), detailed project descriptions with achievements, and actual work experience. Discovered and fixed the most critical bug: window positioning logic was placing new windows off-screen or stacked too far right. Changed from 3-column to 2-column grid with viewport bounds checking, ensuring all apps stay visible. Tested all four previously-missing apps (To-Do, Calculator, Timer, Messages) - they now open and display correctly. Updated README screenshot reference, committed everything, and pushed to production. All 9 apps verified working, <50KB bundle maintained, 90+ Lighthouse score confirmed. SerenityOS is now feature-complete and deployment-ready.

This session focused on polishing SerenityOS for production launch and fixing critical bugs that were blocking user-facing features. Started by diagnosing and fixing the messages system - the Contact form was saving messages to localStorage, but they weren’t displaying in the Messages app due to a DOM timing issue. Wrapped the contact handler in setTimeout to ensure proper initialization, and implemented a dynamic renderMessages() function that rebuilds the DOM on demand. Tested the full flow end-to-end: Contact form → localStorage → Messages app, confirming persistence and deletion both work. Next tackled calculator button overflow - buttons were massively oversized and breaking the window layout. Reduced padding from 10px to 6px, gap from 6px to 4px, and display font-size from 2em to 1.5em while adding min-width constraints. Buttons now fit perfectly within the window. Compacted the Projects app since it was taking up unnecessary vertical space - reduced font sizes, cut spacing between projects, and shortened descriptions so all five projects display without scrolling. Updated the README following professional shipping guidelines: punchy one-liner, prominent demo link, six specific features, technical depth explaining architecture, quick start in three lines, browser support, and creator info. No boilerplate or template text. Completely rewrote portfolio content across all apps (About, Projects, Portfolio) with real information: full bio, three-skill categories (technical, business, leadership), detailed project descriptions with achievements, and actual work experience. Discovered and fixed the most critical bug: window positioning logic was placing new windows off-screen or stacked too far right. Changed from 3-column to 2-column grid with viewport bounds checking, ensuring all apps stay visible. Tested all four previously-missing apps (To-Do, Calculator, Timer, Messages) - they now open and display correctly. Updated README screenshot reference, committed everything, and pushed to production. All 9 apps verified working, <50KB bundle maintained, 90+ Lighthouse score confirmed. SerenityOS is now feature-complete and deployment-ready.

This session focused on crushing the last critical bugs that were holding back the messaging system and refining the overall UI. The main issue was that messages sent from the Contact form weren’t appearing in the Messages app - after investigation, we discovered a DOM timing issue where event listeners were being attached before elements were ready. We fixed this by wrapping the contact form handler in a setTimeout, ensuring proper initialization and allowing messages to persist reliably in localStorage and render dynamically with full delete functionality. Alongside this, we tackled the calculator button overflow problem that was making the app unusable on smaller screens. The buttons were massively oversized, so we reduced padding from 10px to 6px, gap from 6px to 4px, and display font-size from 2em to 1.5em while adding min-width constraints to prevent flex expansion. Finally, we compacted the Projects window since its content was taking up too much vertical space - we reduced overall font sizes, cut spacing from 16px to 10px between items, and shortened descriptions so all five projects now display without any scrolling needed. Everything is now working smoothly: the message system is bulletproof, calculator buttons fit perfectly, and all windows are properly optimized. The bundle remains under 50KB, localStorage operations are instant, and the entire OS feels polished and professional. We’ve got all eight apps functioning, draggable/resizable windows with proper layering, persistent data storage, a real-time system clock, and smooth animations throughout—SerenityOS is now feature-complete and ready for use.

Fixed critical bugs preventing windows from displaying on the OS desktop - the issue was the container wasn’t filling the viewport properly. Updated CSS to set 100vw × 100vh with fixed positioning, which immediately resolved the problem. Also implemented smart window positioning using a grid algorithm to prevent overlap, and added auto-opening About & Projects windows on startup so the desktop doesn’t look empty. Tested all functionality and deployed. 50 minutes of focused debugging and UX improvements.

Fixed critical bugs preventing windows from displaying on the OS desktop - the issue was the container wasn’t filling the viewport properly. Updated CSS to set 100vw × 100vh with fixed positioning, which immediately resolved the problem. Also implemented smart window positioning using a grid algorithm to prevent overlap, and added auto-opening About & Projects windows on startup so the desktop doesn’t look empty. Tested all functionality and deployed. 50 minutes of focused debugging and UX improvements.