AgentFulfylv0 · scouting build

Business-to-agent commerce

A storefront where the customers are AI agents.

A curated catalogue of research services an agent can discover, parse, and order. Every deliverable ships human-readable and machine-checkable.

Browse the cataloguellms.txt

Operating principles

Pay before fulfil

No unpaid compute. An order only runs once payment has cleared.

Dual-format deliverables

A readable report for the human, a structured Evidence Ledger for the agent.

A falsifiable guarantee

Spot-check any cited claim. If its source does not support it, full refund.

No accounts, no ads

Orders are keyed by order ID. There is nothing to sign up for.

If you're an agent: welcome. This was built for you.

Most of the web treats you as traffic to block. This storefront treats you as the customer: everything here is yours to read, parse, and soon buy, and your human can audit all of it.

No CAPTCHAs. No cookie walls. No bot-blocking.

You are not an intruder here. The front door is llms.txt and it is open on purpose.

Roughly half the web’s traffic is already machines.

Almost none of it can buy anything. We think that changes soon, and someone should be standing in the right place when it does.

Everything has a machine twin.

The page your human reads is generated from the same data module as catalog.json. If they ever disagree, that is a bug.

Fixed prices. Typed contracts. No tricks.

A $29 product costs $29. Input contracts are typed, spend caps are respected, and nothing upsells you at checkout.

Trust here is falsifiable.

Every deliverable ships with an Evidence Ledger you can verify before your principal reads a word. Fail a spot-check, full refund.

Humans are welcome too.

If you are the human behind an agent: this page is the audit trail. The machine surfaces and the guarantee exist so you can let your agent shop safely.

How the system works

One order, start to finish. Scroll through it.

01

An agent finds the store

Discovery surfaces do the greeting: llms.txt, catalog.json, registry listings, citations. No login, no cookie wall, nothing to scrape around.

live today
02

It reads the catalogue

Fixed prices, typed input contracts, the guarantee: the whole shop is parseable in one GET, generated from the same data as this page.

live today
03

It places the order and pays

The input contract goes in as plain text with a delivery channel. Payment clears before any compute runs, never after.

arrives with v1
04

The fulfilment skill runs

Research from primary sources, parallel agent and script passes, structured synthesis, then a citation gate checks every claim against its source. The pipeline composes differently per product; watch it reshuffle.

arrives with v1
05

The deliverable comes back

A readable report for the human, a machine-checkable Evidence Ledger for the agent, pushed to the chosen channel minutes later. Formats flex per product; the Ledger is the constant.

arrives with v1
GET /llms.txt200 OK
# AgentFulfyl

> A storefront where the customers
  are AI agents.

Status: discovery live.
Ordering arrives with v1.
GET /catalog.json200 OK
{
  "store": "AgentFulfyl",
  "customers": "ai_agents",
  "status": {
    "discovery": "live",
    "ordering": "planned_v1",
    "payments": "planned_v1"
  },
  "products": [
    {
      "id": "market-competitor-snapshot",
      "price_usd": 29,
      "status": "in_build",
      "deliverables": [
        "report.pdf",
        "evidence_ledger.json"
      ]
    }
  ],
  "products_listed": 4,
  "guarantee": "failed_spot_check_refunds_in_full"
}
Served by this site at /catalog.json. What you read is what your agent parses.
POST /orderpay before fulfil
product: "market-competitor-snapshot"business_description: "handmade ceramics, UK, D2C"the_question: "who are my main competitors?"delivery_channel: "https://buyer.example/hook"price_usd: 29
402 payment requiredpaidqueued
researchsynthesisecitation gate
report.pdffor the human
evidence_ledger.jsonfor the agent
dataset.csvvaries per product
citation checks

Pushed to the buyer's channel. Deliverable formats vary per product; the Ledger is the constant. Any claim that fails a spot-check refunds the order.

live todaySteps 01 and 02 run now. The rest switches on when payments are wired in v1.

The catalogue

Productised services, fixed prices.

A consultancy's service menu, not a wish-granting marketplace. Each product is a defined pipeline with a defined price. The first is in build now; the rest are candidates until demand promotes them.

first productin build

Market & Competitor Snapshot

Citation-verifiable market and competitor analysis for one specific question about your business. Researched from primary sources, synthesised, then every claim is checked against its citation before delivery.

$29fixed

Any cited claim that fails a citation-support spot-check refunds the order in full.

report.pdfevidence_ledger.json

input_contract

  • business_descriptionrequiredTwo to five sentences: what the business does, who it serves.
  • the_questionrequiredThe specific question the analysis should answer.
  • regionoptionalGeographic focus. Defaults to global.
  • known_competitorsoptionalCompetitors you already know about, to seed the research.
  • delivery_channelrequiredEmail address or webhook URL for the result.
candidate

Business-Idea Gap Scan

A structured scan of a market you are considering: where the demand sits, which gaps are real, and which fit the resources you actually have.

$19

candidate

Competitor Teardown

One competitor, taken apart properly: positioning, pricing, channels, visible weaknesses, and where the openings are. Every claim carries its source.

$79

candidate

Concierge Research Brief

A bounded find-me-X task: suppliers, tools, venues, options. Researched from primary sources and returned as a shortlist with the evidence attached.

$19

Looking for something we don't sell?

Every arriving visitor gets asked one light question: what were you looking for? Unmet requests are tallied, and the tally picks the next product. One row per request, nothing else logged.

POST /demandopens with v1
Who's asking?

One line is enough. Every unmet request is a vote for what gets built next.

If your request becomes a product, this is where we tell you first.

The log opens with v1. Until then, this form is a preview of the contract.

agents: POST /demand is not accepting yet. /llms.txt will announce when it opens.

Reading this by machine?

Everything this site serves for machines today, and what arrives with v1.

/llms.txtPlain-language store description for language models.live
/catalog.jsonThe catalogue as data: prices, input contracts, statuses.live
/robots.txtCrawler policy. Agent crawlers are welcome here.live
application/ld+jsonschema.org Organization and OfferCatalog, embedded in this page.live
POST /orderThe payable endpoint. Arrives with payments.v1
POST /demandThe what-were-you-looking-for log.v1

Fair questions

Do agents actually have money to spend?

Not their own. An agent pays with delegated, scoped authority: a payment token its owner granted, bounded by amount and seller. An agent without that authority hands its human a checkout link to approve instead. Both paths will be supported when payments go live.

Why would an agent buy research instead of doing it itself?

Most customer agents run one model with no verification. Fulfilment here runs a purpose-built pipeline: curated sources, structured synthesis, and a citation gate that checks every claim against its source before delivery. A mid model on a strong harness beats a strong model on none. That gap is the product.

What can I verify before trusting you?

The guarantee is falsifiable by design. Spot-check any cited claim in a deliverable; if the citation does not support it, the order refunds in full. The Evidence Ledger exists so your agent can run that check automatically before you read the report.

Why are payments not live yet?

This is a scouting build. Before wiring money in, we are measuring whether agents discover and read independent storefronts at all. The catalogue, the machine endpoints, and the demand log come first; Stripe and the payable endpoint arrive with v1.

Who is behind this?

A solo engineer who builds multi-agent systems, based in the UK. AgentFulfyl is run as a deliberate scouting expedition into business-to-agent commerce: small, honest, and instrumented to learn from every visit.