Resumen
Real-time puntuacion de leads on inbound webhooks: enriquecer via Scavio, apply 12-line weighted rubric in LLM prompt, escribir back to CRM, route to right canal.
Desencadenador
Inbound webhook (form submission, CRM nuevo lead, Salesforce flow)
Programación
Real-time (webhook)
Pasos del flujo de trabajo
1
Catch lead webhook carga util
n8n Webhook node, return 200 fast.
2
Scavio company enriquecimiento
sitio:linkedin.com/company {{company}} → top 3 resultados.
3
LLM rubric scoring
12-line weighted rubric in system prompt, return { puntuacion, reason } JSON.
4
Switch on puntuacion band
Puntuacion >=70 → Slack hot. 40-69 → drip campana. <40 → nurture.
5
CRM write-back
Actualizar lead con puntuacion + reason + marca de tiempo.
6
Optional Slack notificar per band
Hot leads ping AE + resumen.
Implementacion en Python
Python
import requests, os
H = {'x-api-key': os.environ['SCAVIO_API_KEY']}
RUBRIC = """Score 0-100 using ONLY this rubric. Return {"score":int,"reason":"..."}.
Title fit:30 Industry:25 Company size:20 Intent:15 Fit notes:10"""
def enrich(company):
r = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'query': f'site:linkedin.com/company {company}'}).json()
return r.get('organic_results', [])[:3]Implementacion en JavaScript
JavaScript
// Same shape in TS / n8n. n8n is the deliverable.Plataformas utilizadas
Búsqueda web con grafo de conocimiento, PAA y resúmenes de IA