Consultoría AS
11b0ba46fa
Major improvements to AI content generation: ## New Components (app/services/ai/) - PromptLibrary: YAML-based prompt templates with inheritance - ContextEngine: Anti-repetition and best performers tracking - ContentGeneratorV2: Enhanced generation with dynamic parameters - PlatformAdapter: Platform-specific content adaptation - ContentValidator: AI-powered quality scoring (0-100) ## Prompt Library (app/prompts/) - 3 personalities: default, educational, promotional - 5 templates: tip_tech, product_post, service_post, thread, response - 4 platform configs: x, threads, instagram, facebook - Few-shot examples by category: ia, productividad, seguridad ## Database Changes - New table: content_memory (tracks generated content) - New columns in posts: quality_score, score_breakdown, generation_attempts ## New API Endpoints (/api/v2/generate/) - POST /generate - Generation with quality check - POST /generate/batch - Batch generation - POST /quality/evaluate - Evaluate content quality - GET /templates, /personalities, /platforms - List configs ## Celery Tasks - update_engagement_scores (every 6h) - cleanup_old_memory (monthly) - refresh_best_posts_yaml (weekly) ## Tests - Comprehensive tests for all AI engine components Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
82 lines
2.1 KiB
YAML
82 lines
2.1 KiB
YAML
platform: threads
|
|
display_name: "Threads"
|
|
description: "Plataforma conversacional de Meta. Tono más casual y auténtico."
|
|
|
|
limits:
|
|
max_characters: 500
|
|
max_hashtags: 5
|
|
max_mentions: 5
|
|
max_links: 1
|
|
media_optional: true
|
|
|
|
tone:
|
|
style: conversational_authentic
|
|
emoji_usage: moderate # 2-4
|
|
formality: low_to_medium
|
|
energy: friendly
|
|
personal_voice: true # Más "yo" menos "nosotros"
|
|
|
|
formatting:
|
|
line_breaks: true
|
|
use_bullets: optional
|
|
bullet_style: "•"
|
|
whitespace: natural
|
|
paragraphs: short # 2-3 oraciones máximo
|
|
|
|
hooks:
|
|
preferred:
|
|
- pregunta_personal # "¿Alguna vez te ha pasado...?"
|
|
- historia_corta # "Ayer me di cuenta..."
|
|
- opinión_honesta # "Honestamente, creo que..."
|
|
- reflexión # "He estado pensando en..."
|
|
avoid:
|
|
- demasiado_corporativo
|
|
- hooks_de_ventas
|
|
- formalidad_excesiva
|
|
|
|
cta:
|
|
frequency: 0.4 # 40% de posts
|
|
types:
|
|
- engage: "¿Qué piensan?"
|
|
- share: "¿Les ha pasado?"
|
|
- follow: "Más contenido así aquí"
|
|
- discuss: "Debatamos en comentarios"
|
|
style: natural_not_forced
|
|
|
|
hashtags:
|
|
count: 3-5
|
|
placement: end
|
|
style: trending_relevant
|
|
recommended:
|
|
- "#Tech"
|
|
- "#Threads"
|
|
- "#Productividad"
|
|
- "#IA"
|
|
- "#Tips"
|
|
|
|
best_practices:
|
|
- Tono como si hablaras con un amigo
|
|
- Okay ser vulnerable/honesto sobre errores
|
|
- Engagement genuino en comentarios
|
|
- Contenido que invita a conversación
|
|
- Menos "profesional", más "persona real"
|
|
|
|
voice_examples:
|
|
good:
|
|
- "Voy a ser honesto: tardé años en entender esto..."
|
|
- "¿Solo a mí me pasa que...?"
|
|
- "Unpopular opinion: la productividad está sobrevalorada"
|
|
bad:
|
|
- "Nuestra empresa ofrece soluciones innovadoras..."
|
|
- "Estimados seguidores..."
|
|
- "Les compartimos información importante..."
|
|
|
|
adaptation_rules: |
|
|
Cuando adaptes contenido para Threads:
|
|
1. Hazlo más personal y conversacional
|
|
2. Añade opinión o experiencia propia
|
|
3. Invita a la conversación genuinamente
|
|
4. Puedes ser más extenso que X
|
|
5. Emojis naturales, no decorativos
|
|
6. Está bien mostrar vulnerabilidad
|