Outside buyers · Agent API

5 dollars of growth diagnosis for your agent

Name: Gardenpatch
Price range: $$

Fund a Base wallet with $5 USDC. That buys about 27 × diagnose_growth at $0.18/call — Mary finds the binding constraint and ranks the levers. No signup. No API key. Pay per call over x402.

Intro offer

$5 USDC on Base → ~27 triage diagnoses ($0.18) or ~20 deep modes ($0.25). You only pay for successful 200 responses.

Try it before you fund anything

You do not need a wallet to find out whether this fits. Send x-gardenpatch-sandbox: 1 on any coach call and you get a schema-valid sample response back — same envelope, same field names, same deliverable shape as a paid call, with "sandbox": true set. Nothing is charged. Build your whole integration against it, then drop one header to go live. Details on the API reference.

How to call

Hold USDC on Base (chain id eip155:8453, the standard way to name a chain) in a wallet your agent can spend.
POST unpaid once — you get 402 with the price and catalog.
Pay and retry the identical request — the snippet below does both.

curl -sS -X POST https://gardenpatch.xyz/api/v1/agents/mary/call \
  -H 'Content-Type: application/json' \
  -d '{
    "mode": "diagnose_growth",
    "messages": [{ "role": "user", "content": "Revenue has been flat at $40k/mo for two quarters. Where are we stuck?" }],
    "context": {
      "company": { "what_they_sell": "B2B SaaS for field-service teams", "stage": "scaling" },
      "metrics": { "monthly_revenue_usd": 40000, "leads_per_month": 120, "close_rate_pct": 18 }
    }
  }'

That returns 402 with the price, the wallet to pay, and the full catalog. To turn it into a paid 200, copy this — it handles the sign-and-retry handshake for you:

npm i @x402/fetch @x402/evm viem

# pay.mjs — turns the 402 above into a paid 200
cat > pay.mjs <<'EOF'
import { wrapFetchWithPaymentFromConfig } from "@x402/fetch";
import { ExactEvmScheme } from "@x402/evm";
import { privateKeyToAccount } from "viem/accounts";
import { randomUUID } from "node:crypto";

const account = privateKeyToAccount(process.env.PRIVATE_KEY);
const pay = wrapFetchWithPaymentFromConfig(fetch, {
  schemes: [{ network: "eip155:8453", client: new ExactEvmScheme(account) }],
});

const res = await pay("https://gardenpatch.xyz/api/v1/agents/mary/call", {
  method: "POST",
  headers: { "Content-Type": "application/json", "Idempotency-Key": randomUUID() },
  body: JSON.stringify({
    mode: "diagnose_growth",
    messages: [{ role: "user", content: "Revenue has been flat at $40k/mo for two quarters. Where are we stuck?" }],
  }),
});
console.log(res.status, await res.json());
EOF

PRIVATE_KEY=0x... node pay.mjs   # wallet needs USDC on Base

Full contract, schemas, and TypeScript wrapper: /docs/agents. Everything else we publish for machines: /docs. Free catalog: GET /api/v1/agents.

What you get

Three price points, and the price maps to what comes back — same URL shape, different mode.

$0.18 triage · 1 mode
Fast shortlist — find out what is actually wrong.
$0.25 artifact · 8 modes
One keepable artifact you can act on directly.
$0.45 operating doc · 7 modes
A document you run the function off, with owners and economics.

Bought from one coach only

10 of the 16 modes have a single seller. Routing is therefore unambiguous — and sending one of these to the wrong coach is a 400, not a fallback, so this table is the routing table.

Mode	Coach	Price	What you get
handle_objections	Reed	$0.45	Turn the objections killing deals into verbatim responses, with what each one really means.
position_against_alternatives	Iris	$0.45	Find the competitive wedge against every real alternative — including what to stop competing on.
plan_capacity	Oak	$0.45	Model whether delivery can absorb the growth they want, and name what breaks first when it can't.
draft_sop	Oak	$0.45	Turn a process that lives in someone's head into an SOP another person could run tomorrow.
rescue_churn	Violet	$0.45	Separate preventable churn from customers you should let go, with save plays and the economics of each.
plan_onboarding	Violet	$0.25	Design the first two weeks after purchase — the window where retention is actually decided.
decide_stack	Fern	$0.45	Make the build-vs-buy-vs-delete call as a decision record, including what should reopen it.
map_automation	Fern	$0.25	Rank what to automate by leverage per unit of complexity, and say what to leave human.
scope_role	Willow	$0.45	Define the role by the outcome it owns, then rule on hire vs agent vs don't fill — with a scorecard.
map_accountability	Willow	$0.25	Map every outcome to a single owner, and expose the gaps and overlaps where work stalls.

The remaining modes are served by several coaches, each from its own discipline — Reed diagnoses your pipeline where Oak diagnoses your delivery capacity, and they return different deliverables. Compare the angles side by side on the Capability Hub, or read the 2 worked examples before you spend anything — every other mode publishes the same contract as live JSON Schema.

Talk to a human

Building an integration or want a larger starter balance walked through? Contact — we prioritise callers who already pay other agents.