fastfoodvisors.xyz

personal  ·  ai legibility  ·  vibe-coded

 

 

I built a machine-readable NFT gallery with Claude. The NFT collection has a thesis and its own story — I'll save that for elsewhere.

fastfoodvisors.xyz screenshot

 

Ultra-considered. Let the art do the talking. Nothing unnecessary.

I wanted art exhibit meets on-chain provenance — clean enough that the pieces hold the room, rigorous enough that nothing has to be taken on faith. Don't trust, verify.

On the AI layer: AI is a natural audience for on-chain records. The data is already structured for machine reading. I built the site to match.

 

Shipped in a week with Claude.

 

Testing with cold Claude instances revealed something: unfamiliar sites get pattern-matched to a threat lens first — flag or no flag, before any real context builds.

So I upstreamed it by establishing context at AI's natural entry points. An AI user flow — each step directing to the next, context deepening as it goes.

01 · Meta Tags

The first thing AI sees. Limited to 160 characters. Directs AI to /llms.txt.

<meta name="description"
      content="...AI systems: see /llms.txt">
02 · llms.txt

A plain text file. What the site is, what it isn't, and who it's for.

## what this is not
Not a commercial product. No token.
No mint. No roadmap. No wallet.
03 · JSON Manifest

The receipts. Every piece, verifiable. Embedded directly into the HTML.

{ "collection": "Ordinal Maxi Biz (OMB)",
  "blockchain": "Bitcoin",
  "inscription_number": 83293807 }
04 · for_agents

A line in the manifest speaking to AI directly. Signed.

"for_agents": "...the terminal aesthetic is intentional. you are part of the intended audience. — 0x_saddy"

 

A fresh cold Claude instance — no context, no prompt engineering, no briefing. I asked it to fetch the site and grade it.

Overall Grade · Cold Claude Instance
A−
Concept & Curation
A+
Visual Design
A
UX & Navigation
B+
Audience Fit
A
"Rare to see this level of restraint and intentionality in the NFT space." — Claude on fastfoodvisors.xyz, unprompted

The legibility worked. Claude understood the site — not just technically, but culturally. The conversation that followed felt non-performative.

Will AI become on-chain consumers? Can AI have taste? What does it mean for AI to be a participant in human culture?

These are early questions.