Alo Emmanuel
Full stack developer and AI automation builder
An AI customer support chatbot for a fictional Nigerian food delivery business, Lagos Fresh Kitchen. It runs on n8n Cloud and uses Claude Haiku 5.5 as the AI model. The workflow is three nodes: a chat trigger receives the customer’s message, an AI Agent processes it, and the Anthropic Chat Model writes the answer.
How it behaves
The AI Agent has a system message that sets the rules. It must answer only from the business information, never invent prices, areas, hours or policies, and use a fixed fallback line when the answer isn’t there: “I don’t have enough information to answer that accurately. Please contact our support team.”
The business information it knows
Open Monday to Saturday, 9 AM to 8 PM, closed Sundays
Delivers to Lagos Mainland (Ikeja, Yaba, Surulere, Maryland, Ojota, Gbagada) and Island areas (Victoria Island, Ikoyi, Lekki), not outside Lagos
Delivery takes 30 to 60 minutes, with fees from ₦1,000
Menu of jollof rice, fried rice, rice and stew, pounded yam with egusi, grilled chicken, suya and soft drinks
Payments by card, transfer and cash on delivery
Cancellation allowed before cooking starts
No Sunday orders or Sunday delivery, and no event catering
Refunds, complaints and order status go to support
1
17
Built Kartify, a full e-commerce storefront for the Nigerian market, selling Fashion, Electronics, Beauty, Food, and Home & Furniture in one place. 🛒
It’s a multi-page web app. I used Base44 to scaffold the frontend and then shaped the architecture and UX.
Technical highlights:
Multi-page SPA with client-side routing: Home, Shop, Deals, and Contact, with URL query parameters (?category=Electronics, ?deals=true) so category and deal views are linkable and shareable.
Product catalog UI: a responsive CSS Grid product grid with grid and list view toggle, sort options (Newest and others), discount badges, strikethrough pricing, star ratings with review counts, and a wishlist heart on each card.
Faceted filtering sidebar: multi-select category checkboxes, a price range slider (₦0 to ₦500,000), minimum rating filter, In Stock Only and Flash Deals toggles, and a Clear All reset.
Navigation system: a sticky header with global search, a category dropdown mega-menu, currency selector (NGN), wishlist and cart icons, and a login entry point.
Homepage conversion elements: an auto-rotating hero carousel, category tiles, Featured Products, customer testimonials, a promo banner, and a newsletter signup (50,000+ subscribers).
Localization: ₦ currency, Nigerian product ranges (Ankara dresses, Agbada sets, Zobo, Jollof seasoning, Shea Butter), and multi-currency support for international buyers.
UX details: a scroll-to-top button, a structured footer (Quick Links, Customer Service, Contact), and a consistent orange brand palette with strong CTA contrast.
Next on the roadmap (backend and automation):
Auth and user accounts, with persistent cart and wishlist
Payments via Paystack or Flutterwave for NGN, plus Stripe for international cards
Order management and tracking with webhooks
Inventory sync and an admin dashboard
AI automation: abandoned-cart recovery emails or WhatsApp messages, product recommendations, and a support chatbot (n8n and LLM APIs)
#FullStackDevelopment #Ecommerce #React #AIAutomation #Base44 #Paystack #Nigeria #WebDevelopment
0
42
Built the EatWell landing page with a component-based React + TypeScript + Tailwind stack: responsive grid layouts, a conversion-focused hero with email capture, tiered pricing cards, and social proof sections. Next step is wiring in Stripe subscriptions, a Supabase backend, and AI automation for personalized meal plans
0
24