Back to products
Case study · AI calling platform

Growth Intel Lab

An AI calling platform that researches leads, calls them with a real-time conversational AI voice, and answers incoming calls — with no human needed on the line.

Live
Visit Growth Intel Lab

The problem

Businesses lose leads and customers because nobody has time to call every lead, follow up on time, or answer every incoming call.

What I built

  • Import leads from CSV/Excel or a single Google Maps link; AI reads and organizes messy files automatically
  • Researches each business on the web before calling and drafts a call plan for that specific lead
  • Places real phone calls with a real-time two-way AI voice that follows a persona, script and campaign goal, in multiple languages
  • Calls through a cloud phone line or the user's own SIM card, using GIL Gateway — an Android app I built that turns a phone into an AI calling line
  • AI receptionist answers incoming calls, takes messages and emails a summary afterwards
  • Every call is recorded, transcribed and summarized, with an extracted outcome (interested, callback, meeting, not interested)
  • A supervisor can listen live, guide the AI mid-call, or take over the call and hand it back
  • Automatic retry rules for failed calls, with a plain-English reason for every failure
  • Smart Desk: "call this person, ask this, tell me what happened" tasks, with results sent by email or WhatsApp
  • Raven: a voice and chat assistant that controls the app ("call Ahmed tomorrow at 10 and confirm the order")
  • CallHub: incoming calls ring the team in the browser first, then the AI picks up if nobody answers
  • Career Agent: applies for jobs on a candidate's behalf — tailored CV, emails, follow-ups and interview prep
  • Installable app (PWA) with push notifications, and a usage-and-cost dashboard for every AI feature

How it's built

One Node.js app serving a React front end and a REST + WebSocket backend. Phone audio is streamed in real time between the phone network and Raven AI, the real-time voice model. A MySQL-backed job queue runs research, calling and follow-ups unattended. The Android gateway app injects the AI's voice directly into a live cellular call.

  • Raven AI
  • Node.js
  • React 19
  • TanStack Start
  • MySQL/MariaDB
  • Kotlin (Android)
  • Hostinger

My role · Designed, built, deployed and maintained solo with AI-assisted development (Claude Code).

Proof

  • Live at growthintellab.com
  • First real campaign: 697 leads imported from one file; about 75 real calls placed in a single afternoon, unattended
  • AI answers in about 2 seconds after the person stops speaking (median, measured on real calls)
  • AI receptionist has answered real incoming calls end to end, with transcript and summary saved

Screenshots

Build with me

Need a product built? Let's talk.

Hiring for a leadership role? Book an interview