Agent-First Commerce: I Built a Website That Sells Like a Sales Team
Over a weekend, I built and tested a working Agent-First e-commerce demo with Claude Code, MCP, and conversational checkout. Here's what I learned.

π Introduction
Not selling anything here β just sharing what I built over a weekend using Claude Code, the Model Context Protocol (MCP), and Agent-to-Agent (A2A) orchestration.
The idea was simple: > Could a website behave like a full sales team β not just a storefront, but a conversation-led experience where agents guide, pitch, and close?
So I prototyped it.
It works. You can test it live right now at fabiangwilliams.com
π§ What Is Agent-First Commerce?
Traditional e-commerce relies on catalogs, carts, and checkouts.
Agent-First Commerce introduces a conversational pipeline where AI agents assume roles:
- A Greeter Agent welcomes and routes the user
- A Sales Agent explains the product and handles objections
- A Checkout Agent sends a secure Stripe link to your inbox
Everything is driven by structured conversation.
πΌοΈ Walkthrough: What the Agent Experience Looks Like
1. Welcome to the Agent-First Store
You’re greeted by a clean call to action β powered by AI agents.
2. Start a Conversation
Say hello or click a button β and you’re instantly chatting with a Greeter Agent.
3. Product Discovery in Chat
The Sales Agent presents offerings like a live rep might do in-store.
4. Pitch the Product
When you pick something (like a latte), the Agent explains what it is and asks for a decision.
5. Confirm Purchase in Chat
The Sales Agent offers to process your order via secure email checkout β no cart needed.
6. Email Checkout via Stripe
You receive a branded email with a Stripe link β no payment inside the chat itself.
7. Checkout Using Stripe Test Mode
Try it yourself using Stripe’s test card numbers.
8. Confirmation & Fulfillment
Youβre thanked, confirmed, and shown what happens next.
π οΈ Tech Stack
This was built using: - Frontend: Next.js + Stripe Elements - AI Orchestration: Semantic Kernel + MCP server - LLM Pairing: Claude Code + GitHub Copilot - A2A Agent Flow: Greeter β Sales β Checkout (via MCP tool chaining) - Checkout: Stripe (Test mode)
All logic was coordinated via local Semantic Kernel plugins and MCP tool endpoints using HTTP-based coordination between agents.
π‘ Key Learnings
- Agent-to-Agent flows feel surprisingly natural to users.
- No-cart, chat-based checkout reduces friction and bounce rates.
- Stripeβs hosted email link checkout increases security and trust.
- Claude Code is excellent for quick prototyping and planning across LLM chains.
π Try It Yourself
π§ͺ Live Demo β fabiangwilliams.com
π¬ Works best if you “buy me a latte” β it’s a full test flow from chat to email to checkout.
π Stripe is in test mode β no real charges are made.
π¬ Final Thoughts
This is early work, but it proves a point:
> Websites donβt have to be static pages β they can act like a sales team.
As agent architecture, orchestration protocols like MCP, and LLMs mature, I believe weβre entering a new era of agent-forward web design β one driven by structured dialogue, instant utility, and seamless integration.
I’m continuing to iterate on this. Feel free to reach out if you’re working in this space.
Connect With Me
Platform | Link |
---|---|
Fabian G. Williams | |
BlueSky | @fabianwilliams |
fabian@adotob.com |