Resumen
One-time per-client setup: recopilar samples, LLM analiza voice characteristics, salida 1-pagina fingerprint YAML almacenado in version control. Per-content-task: pull live samples via Scavio + apply fingerprint.
Desencadenador
On-demand (one-time per cliente, plus quarterly refresh)
Programación
Quarterly (refresh) + on-demand (per tarea)
Pasos del flujo de trabajo
1
Recopilar 50-100 sample artifacts (publicaciones, correos electronicos, transcripts)
Real cliente salida, no aspirational.
2
LLM analizar: sentence longitud, vocabulary, signature openers, tone descriptors
Salida structured YAML.
3
Save fingerprint to ./brand-voices/{slug}.yaml
Version control for auditability.
4
Per contenido tarea: Scavio pulls 3 live reciente samples
sitio:CLIENT.com OR sitio:linkedin.com/in/CLIENT for currency verificar.
5
LLM compose con fingerprint + samples + brief
Static + dynamic anchor.
6
QA: spot-check 1-of-5 contra fingerprint
Catches drift sobre time.
Implementacion en Python
Python
import requests, os, yaml
H = {'x-api-key': os.environ['SCAVIO_API_KEY']}
def live_samples(slug):
r = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'query': f'site:linkedin.com/in/{slug}'}).json()
return r.get('organic_results', [])[:3]
def compose_for_client(slug, brief):
fp = yaml.safe_load(open(f'./brand-voices/{slug}.yaml'))
samples = live_samples(slug)
return f'Fingerprint: {fp}\nSamples: {samples}\nBrief: {brief}'Implementacion en JavaScript
JavaScript
// Same in TS.Plataformas utilizadas
Búsqueda web con grafo de conocimiento, PAA y resúmenes de IA