Meet Laila. The jewellery concierge that listens. A fully deployed AI sales assistant for Astraea Fine Jewellery — built from scratch in weeks, live in production, and capable of selling in various languages through text, voice, and image. WHAT WAS BUILT Not a chatbot. A concierge. Laila is an AI-powered sales assistant embedded directly into Astraea Fine Jewellery's website. She understands what a customer is looking for — by reading what they type, listening to their voice, or analysing a photo they share — and responds the way a trained in-store stylist would: with curated product recommendations, elegant replies, and a genuine sense of the brand. FOR BUSINESS OWNERS Your best salesperson. Available always. Laila answers customer questions at 2 am in Arabic, recommends a pearl necklace to someone browsing in Hindi, and helps a French speaker find the perfect anniversary gift — all without a single human agent involved. She knows your entire catalogue, never pushes too hard, speaks the customer's language naturally, and sends them directly to checkout with one tap. Think of her as your most consistent, most patient, most knowledgeable team member — who never calls in sick. Updating the catalogue is as simple as editing a spreadsheet. No developers, no deployments. FOR TECHNICAL EVALUATORS Production-grade. Auditable. Extensible. A single-file HTML shell loads two external JS modules (config.js, catalog.js) and communicates exclusively with a Deno Deploy edge proxy. No API keys, prompts, or webhook URLs are exposed in page source. The proxy abstracts four backend layers: Make.com automation (8-route GPT-4o scenario), ElevenLabs TTS, Airtable catalog, and OpenAI Whisper transcription. The catalog provider is hot-swappable via a single env var — Airtable today, Cloudflare D1 or KV tomorrow. Conversation history persists in a Make datastore keyed by sessionId. The architecture is fully stateless on the client — drop-in replaceable at every layer.

There are now two ways to build AI automations, and most people are picking the wrong one. This video compares the two leading approaches: the visual canvas of n8n versus the AI-powered generation of Claude Code. Whether you're building for your own business, running an agency, or just need to build a custom solution, this guide will help you decide which tool you should be using. Check it out 👇👇

In this video, I’m going to show you the real AI voice agents businesses are paying $12,000 or more to build and have been using for years. This video will give you a clear picture of where the voice AI market is actually heading and which opportunities have the most potential. Make sure to stick around until the end, because I’m also going to be revealing a use case I would highly recommend staying away from... Drop a comment on the video, it helps out alot 👇

Hey everyone 👋I’m Sanjay Adnani, based in Dubai. I’ve spent the last 3+ years building automation systems using Airtable + Make, and over the past year I’ve been integrating AI into these workflows to drive real efficiency gains. Most of this work has been hands-on for a jewelry brand, where I’ve built end-to-end systems covering: - Product image cleaning & AI model image creation - Inventory management + automated indent generation - Streamlined backend ops across teams Recently, I also built my first AI voice bot using Telegram + n8n, which was a fun step deeper into conversational AI + automation. A lot of this work isn’t fully reflected on my LinkedIn yet — more building than posting mode. Excited to learn, share, and connect with people serious about automation, AI, and scalable systems ..If you’re in or visiting Dubai, happy to connect in person🚀