Converc — Turn Website Visitors Into Live Conversations
URL: https://converc.com
One-liner
Built a real-time browser-based calling platform from scratch — MVP live in 5 days.
Project Overview
Converc solves a problem that costs B2B companies revenue every day: high-intent visitors land on your site, can't get a human immediately, and leave. It embeds a call widget that connects visitors to sales reps in real time — no booking links, no forms, no friction.
I architected and built the full product: a Next.js frontend, Supabase backend with Row Level Security, and WebRTC-powered peer-to-peer audio calling that works entirely in the browser with no native app required. The stack was chosen for performance, low latency, and the ability to ship fast without sacrificing production quality.
What I Built
WebRTC call engine with real-time signalling via Supabase Realtime
Embeddable call widget (drop-in script for any website)
Agent dashboard with live call status, queue management, and session history
Webhook integration layer for CRM and Slack notifications on call events
OAuth-based authentication with Google and dev/prod environment separation
Supabase RLS policies enforcing strict data isolation between workspaces
How I Shipped It
The core MVP — widget, signalling, agent dashboard, and working calls — was shipped in 5 days using Cursor with Claude as the AI pair programmer. Post-MVP work covered Google Safe Browsing clearance, Slack App submission, analytics scoping, and hardening the auth and security model for production.
Tech Stack
Next.js · Supabase · PostgreSQL · WebRTC · Vercel · Tailwind CSS
0
365
FILL — AI Cancellation Recovery for MIRROR 27
I built FILL for MIRROR 27, a boutique salon in Indiranagar, Bengaluru, to solve a simple but expensive problem: last-minute cancellations leave valuable appointment slots empty, and salon owners have to manually chase customers through WhatsApp to fill them.
FILL turns that entire follow-up process into an automated recovery flow.
How it works
A customer cancels an appointment.
FILL immediately understands the service, duration, stylist, time slot, and value of the opening.
It searches the salon’s existing customer/inquiry pool for people who are likely to take that exact slot.
Customers are ranked with an easy-to-understand match score.
The owner can review the best match and send an offer.
The customer receives a simple mobile experience: “A spot just opened for you ”
With one tap, they can claim this appointment.
Once accepted, the appointment is automatically confirmed, and the owner’s schedule is updated.
If the customer declines or the offer expires, FILL can continue with the next suitable customer.
The key idea
Don’t let cancellations become empty chairs.
Instead of giving salon owners another complicated dashboard or booking system, FILL focuses on the moment where money and time are actually lost — the follow-through after a cancellation.
The owner shouldn't have to search old conversations, remember who wanted a particular service, or send multiple WhatsApp messages.
FILL finds the opportunity, finds the customer, and helps turn the empty slot back into a confirmed appointment.
What I focused on
Simple owner experience
Minimal manual work
Customer-first mobile booking flow
Explainable AI matching
Shared Owner ↔ Customer appointment state
Cancellation, rescheduling and confirmation flows
Clear recovery feedback such as ₹3,200 recovered
Premium, approachable salon UI without making the product feel
overly technical
Business: MIRROR 27
Location: Indiranagar, Bengaluru
Product: FILL
Core problem: Empty appointment slots caused by last-minute cancellations
Solution: Automatically match and recover those slots with the
right customer.
2
1
177
I designed and developed the Highflame website, creating a modern and professional digital presence for their AI security platform.
The work focused on presenting complex AI security, agent identity, authorization, and governance solutions in a clear and easy-to-understand way. I worked on the website structure, responsive design, page layouts, and overall user experience to make the platform appealing to enterprise and technology-focused audiences.
0
163
I built something wild for the Paper Challenge🚀
It turns any GitHub repo into a visual case study — instantly.
No writing. No designing.
Just drop a repo link… and the canvas builds itself.
That’s CodeSage💯
Most devs have solid projects…
but they’re buried in README files nobody reads.
CodeSage changes that.
It reads your actual code — architecture, stack, commits —
and transforms it into a clean, dark, presentation-ready case study.
The real unlock?
Paper MCP.
I connected my AI agent directly to the canvas.
So instead of designing manually…
the agent builds everything:
• Sections
• Layout
• Insights
• Structure
All generated directly on the canvas.
No drag. No drop.
Just output.
Pick any repo → get 3 analysis modes:
*Each one gives
→ Complexity score
→ PR velocity
→ Language breakdown
→ Full Refactor Roadmap
Try CodeSage: https://codesage-871524277866.us-central1.run.app/
Tech stack:
Paper MCP · Gemini API · GitHub API · Antigravity
22
58
1.3K
