Built a voice agent for vendor follow-ups and customer ops on OpenAI’s GPT-Live-1 API. In a small test with 4 users, it felt instant and natural.

That’s not the same as ready for a client.

Before I’d hand something like this over (or open it to more users), I want to see: → Speed holding up as concurrent calls increase → Interruptions handled cleanly on real phone audio → Names, IDs and phone numbers captured correctly → Calls that end properly, plus graceful fallbacks when something times out or drops → Real cost per minute, including the backend model

A demo that works and a product that holds up are different jobs. I’m working on closing that gap now.

If you’ve shipped a voice agent for a client, what broke first? Open to a few voice-agent projects this quarter

AI WhatsApp Support Assistant (n8n Automation Demo)

Problem: Small businesses lose customers when WhatsApp messages sit unanswered, leads get buried in chats, and complaints are noticed too late.

What I built: An AI assistant that reads every incoming WhatsApp message and prepares a reply, while the owner stays in control.

Writes a reply draft from the business’s own info sheet. Nothing is sent until the owner approves it by email.

Captures real leads (name, interest, budget) into a Google Sheet.

Saves orders and appointment requests with a draft confirmation.

Alerts the owner on Discord for complaints and “talk to a human” requests.

Transcribes voice notes and handles them like text messages.

Alerts the owner to reply manually when someone sends an image or sticker.

Posts a daily 9 PM summary of the day’s conversations to Discord.

Role: Nisbah Iqbal, AI Automation Builder