In November 2025 Collins named vibe coding its word of the year: describing what you want in plain words and letting AI write the code. I understand why people would call what I do vibe coding. It is a useful doorway phrase. It does not describe how this shop was built.
Eighteen months of the loop
teas.co.uk took about eighteen months of building, stepping back, finding where things had drifted, writing down exactly where we stood, correcting it and going again. Vibe coding gets you moving. The loop is what stops the thing falling apart the next morning:
- Build one piece.
- Inspect what actually came out, on the live site, not what the machine says it did.
- Write down the new state in a handover note, so the next session starts from the truth.
- Go again.
Every change to this site still runs that way, including the Tea Wiki of 1,924 entries and the 402 products from 40 brands in the shop. The handover notes are the most valuable files I own.
Several AI models, on purpose
I do not use one AI. I use several AI models, often on the same problem at once. What I am after is not answers. It is argument. One model sees the structure. One finds the gap. One catches a claim too strong to stand behind. One flatters me and is wrong, and I have to be sharp enough to notice.
The rule I took from that is on my founder page: check the machine's work. The responsibility stays with the person whose name is on the shop, which is why the site keeps built and planned firmly apart.
Paper first
I plan on paper, on purpose, even for the parts machines will read. Three lists before I touch a computer:
- the questions customers actually ask;
- the proof a stranger would need before believing us;
- the things nobody has bothered to write down that only someone in the trade would know.
Those lists became the product facts, the claim boundaries, the complete payload an assistant can ask for, and the Tea Wiki.
What it takes
The real cost is time: months of evenings before anything is good. One early job, rewriting roughly 300 product pages with AI and checking every suggestion myself, took about four weeks. The machines make the work faster. They do not make it shorter than it needs to be.
Open standards, so assistants can shop
The tools for connecting assistants to a shop are now open standards. teas.co.uk runs a server using the Model Context Protocol, an open standard introduced in November 2024, so that since 6 October 2026 an assistant can search our catalogue and fill a basket while the customer still checks out and pays on teas.co.uk. I explain the rest of the build in What's inside a tea shop built for AI to read, and Under the Hood publishes what we can measure and where the evidence stops.
What I would tell anyone starting
Start with the thing you know better than most people alive, not the technology. Keep a written record of where you are. Ask more than one machine, and believe none of them until you have checked. Then publish what you can prove. Your "only" might be the whole trade.
What others have found
Outside research and reporting that bears on this, with links to the original sources.
- Search Engine Journal's Selling to AI: the complete guide to agentic commerce describes AI shopping agents that already find products and complete purchases.
- Slobodan Manic argues in Search Engine Journal that agentic commerce is a structural change but still unproven (Search Engine Journal).
- llms.txt is a proposed standard for telling language models what a site contains; teas.co.uk publishes one.
- Google's guidance on helpful, reliable, people first content asks who created a piece, how, and why.
Read more
- What the motor trade taught me about building a tea shop for AI
- Built versus planned
- Most of the web is closing the door to AI. We opened ours.
- Meet the founder
Lee Samuel Tucker
Founder, teas.co.uk
Tunbridge Wells, Kent
