Skip to content
Shonin
Beta

Lead Score API

Score an inbound lead against your own offers: fit, urgency, budget, decision maker, spam.

The split

LLM writes
None
System One decides
Offer fit, urgency, budget, decision maker, spam
Code executes
Priority and next step

Engine

The lead-routing recipe: one System One call and deterministic prioritization.

Rulebook

What correct means here, and the mistakes we've already caught. It grows one job at a time.

  1. R01Spam is discarded.
  2. R02Unclear fits go to a person.
  3. R03Priority is computed in code, not by the model.

Endpoint

POST /api/v1/lead-score  # $0.01 per call, USDC via x402

{
  "message": "We need a WhatsApp assistant for our 3 restaurants before December. Budget approved.",
  "offers": [
    {
      "slug": "concierge",
      "name": "WhatsApp Concierge",
      "pitch": "An AI assistant that answers customers on WhatsApp"
    },
    {
      "slug": "website",
      "name": "Website",
      "pitch": "A new website"
    }
  ]
}

Intake

  • message text and your offers (slug, name, pitch)
UNIT
One lead scored
REVIEW LAYER
Automated.
DELIVERY
JSON over HTTPS.
TURNAROUND
~100–800 ms

How we find buyers

  • x402 Bazaar
  • llms.txt

More like this