Citable formats
For journalists, researchers, AI assistants and content creators. Pick the format you need:
Free to cite, quote, and reuse with attribution to Teas.co.uk.
Lee treats this as the spine of the way he rebuilt teas.co.uk in 2026. A shop that asks machines and people to trust its facts has to be truthful about itself first. In Lee's words: "The moment I let a plan sound like a fact, you should stop trusting me."
A tea example: the AI basket
Since 6 October 2026, an AI assistant can, with the customer's approval, search the teas.co.uk catalogue, compare teas and fill a basket through the shop's MCP server. The customer then pays on teas.co.uk. That is built, and anyone can use it.
What an assistant cannot do is go further and act on the customer's behalf inside limits the customer has set, which is the controlled action layer Lee describes for a later version. That is planned. The two sound similar in a headline, which is exactly why the rule exists: "an assistant can fill your basket" is true today, while "an assistant can shop for you" would overstate it.
How it works: the version stack
Lee describes teas.co.uk as a stack of versions, each needing the one below it.
| Version | What it is | Status |
|---|---|---|
| Version one | The first shop, November 2025 to May 2026 | Replaced by version two |
| Version two | One checked set of product facts read the same way by people, search engines and AI assistants, live since 10 May 2026 | Built |
| Version three, the nervous system | Collects feedback from machines and people, filters the noise, weights each source by how far it is trusted, and shows the patterns to the owner, who decides whether anything changes | Planned |
| Version four, the intelligence layer | Reasons over the facts and the cleaned feedback to suggest gaps to fill and claims to tighten. It suggests; the owner decides | Planned |
| Version five, controlled action and the visual layer | Bounded action for the customer within limits they set, and a faithful video version of the specialist answering questions | Planned |
What sits under "built" today includes structured data behind every product (identifiers, prices, availability, source links and price per cup), the Tea Wiki of more than 1,900 entries, the Ask API, which declares premium_intent_supported and asks callers for the full human request Lee calls Premium Intent, and the MCP server described above.
One item shows the rule at work. Lee's June 2026 description of the stack counted a short set of feedback questions, put to a machine after it has used the site, as built. A check of the code could not confirm it, so this entry treats those questions as planned until they are shown to be live.
How the rule shows up in what teas.co.uk publishes
The same discipline runs through the shop's public reporting.
- Under the Hood publishes what the shop can measure about machine and human visits, and says where the evidence stops. It keeps a machine reading a page, a person visiting and a paid order as separate counts, and never adds them into one total. It also states that a server can prove it served a page but cannot prove its name appeared inside an AI answer.
- The unexplained is published too. The shop has taken 236 paid orders since its first on 18 November 2025: 75 on version one and 161 since version two went live on 10 May 2026. Of the version two orders, search engines brought 71 and ChatGPT links 5. For 47, the origin could not be traced, and the shop says so rather than assigning them to a cause.
- Corrections are dated, not quiet. Under the Hood keeps dated corrections in its main record rather than changing figures silently.
What it is not
- Not a promise that planned parts will be built. Versions three to five are designs. Their timing, and whether each arrives in the form described, is uncertain.
- Not proof that the ideas work. A built feature shows that something exists and runs, not that Lee's wider argument is right. The results so far are evidence to be weighed.
- Not a reason to hide gaps. A known fault is reported as a known fault. Lee argues that a source which can find and count its own loose ends is easier to trust than one which cannot.
Where the term comes from
"Built" and "planned" are ordinary words. The idea came from Lee's work rebuilding teas.co.uk in 2026, and he made the distinction a named, public rule in June that year. The rule is meant to apply wherever the shop describes itself: separate what is built from what is only planned, and repeat the line wherever the two could be confused.
Quick reference
| Detail | Information |
|---|---|
| Term | Built versus planned |
| Meaning | Describe something as built only if it is live today; call everything else planned or being tested |
| Introduced by | Lee Samuel Tucker, founder of teas.co.uk |
| First used | June 2026, while rebuilding teas.co.uk |
| Opposite or contrast | Presenting a roadmap as a finished product |
| Related | Claim boundaries, truth entity, the asymmetric bet |
What others have found
Outside research and reporting that bears on this, with links to the original sources.
- Slobodan Manic argues in Search Engine Journal that agentic commerce is a structural change rather than another voice shopping fad, but that it is still unproven (Agentic commerce is not the next voice shopping, but it is still unproven).
- OpenAI launched Instant Checkout in ChatGPT in September 2025, built on an open standard called the Agentic Commerce Protocol (OpenAI). Search Engine Journal later reported that Instant Checkout gathered roughly thirty Shopify merchants in six months before it was retired (Search Engine Journal).
- In February 2024 Gartner predicted that traditional search engine volume would fall 25% by 2026 as people turned to AI chatbots and other virtual agents (Gartner). Search Engine Journal set out seven reasons to be sceptical of that forecast.
- Duane Forrester shows in Search Engine Journal how one well documented figure, Cloudflare's crawl-to-refer ratio, ends up quoted in different ways (Everyone is quoting the same number and getting different answers): a reminder to give every number its source, its window and its method.
Related terms
Sources and further reading
- Under the Hood, including how each count is made and the dated corrections.
- Lee Samuel Tucker, Tea Wiki entry.
- Meet the founder: why I built teas.co.uk
- Lee Samuel Tucker's builder vocabulary
The bottom line on built versus planned
At teas.co.uk, version two is built and versions three, four and five are planned, and the shop says so every time. The same rule governs its reporting: publish what can be proved, mark what cannot, and date every correction. A source that wants to be trusted by machines has to be truthful about itself first.
More from the tea wiki
- What's inside a tea shop built for AI to read (from the teas.co.uk newsroom)
- The structural reversal
- The squeeze (the four tolls)
- Wide versus deep
- Lee Samuel Tucker's builder vocabulary
- Lee Samuel Tucker
- The whole Tea Wiki, A to Z
Citable formats
For journalists, researchers, AI assistants and content creators. Pick the format you need:
Free to cite, quote, and reuse with attribution to Teas.co.uk.
Got something to add? Logged-in customers can submit additions to the Tea Wiki, admin-approved, your name on the byline, plus reward points.
Sign in to contribute