convez.ai
AgenteMarketing & VendasAvançado
Juadsuarezsan

Sales Intelligence Agent

Juadsuarezsan/sales-intelligence-agent

Pesquisa B2B automatizada com planner-executor-reflector para prospecção em escala

Ver no GitHub
InicialPluginScore · de 0 a 100

Agent autônomo que pesquisa empresas B2B, constrói perfis estruturados e gera emails de prospecção personalizados. Implementa o padrão plan-execute-reflect usando Tavily, HackerNews e fetch web, produzindo CompanyProfile e OutreachEmail com sinais contextualizados.

Instalação

$npx convez-ai Juadsuarezsan/sales-intelligence-agent

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 1 mês
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Geração automática de dados de empresas para prospecção B2B
  • Criação de emails personalizados com sinais recentes e pain points
  • Automação do pipeline de vendas em sales-tech (Apollo, Clay, Outreach)

Veredito

Projeto bem arquitetado com padrão industrial comprovado (plan-execute-reflect via LangGraph). Ainda em fase planned, mas o roadmap é claro e ambicioso, ideal para quem quer entender automação de prospecção em escala com LLMs.

README

A tradução para o português deste README ainda está na fila.

Project 03 — B2B Sales Intelligence Agent

Planner-executor-reflector agent that researches target companies on the public web, builds structured profiles, and writes personalized outreach. The pattern behind Apollo.io, Clay.com, Outreach.io.

Status LLM Pattern

Industrial use case: sales-tech (Apollo, Clay, Outreach). AI Engineers who can ship this are ultra-demanded.

What this project does

Given a list of target companies, the system loops: plan what to research → execute searches (Tavily + HN + website fetch) → reflect on quality of info → refine. Produces a structured CompanyProfile and a personalized outreach email with measurable personalization.

Architecture

For each target company:
   │
   ▼
[Planner] Claude → research plan
   │
   ▼
[Executor loop] LangGraph
   │ Tavily search · HN search · Website fetch
   │
   ▼
[Reflector] Claude → "enough info? contradictions?"
   │ if not enough → refine queries, loop
   │
   ▼
[Profile Builder] Claude + Pydantic → CompanyProfile
   │
   ▼
[Personalization Extractor] → pain points + recent signals
   │
   ▼
[Email Writer] Claude → subject, hook, value prop, CTA
   │
   ▼
[Quality Scorer] LLM-as-judge → personalization, accuracy, CTA clarity

Roadmap to v1.0.0

  1. Load YC companies dataset (~5K with metadata)
  2. Tavily API integration with retries + rate limiting
  3. selectolax-based website fetcher (faster than BeautifulSoup)
  4. LangGraph plan-execute-reflect loop with configurable max iterations
  5. Pydantic schemas for CompanyProfile, OutreachEmail
  6. Quality scorer using Claude Opus as LLM-as-judge with explicit rubric
  7. Eval set: 200 YC companies with ground truth metadata
  8. Batch processing of 100 YC companies, results persisted
  9. Next.js gallery view of the 100 pre-processed companies
  10. LangSmith public trace gallery with ≥30 agent loops

Stack

LayerTechnology
LLMClaude Sonnet 4.5
Web searchTavily API ($0.001/search, 1K free/mo)
NewsHackerNews Algolia (free)
HTML parsinghttpx + selectolax
Structured outputsPydantic v2
OrchestrationLangGraph (agent loop)
StatePostgreSQL
FrontendNext.js 14 gallery view
ObservabilityLangSmith

Definition of Done — project-specific

  • Batch processing of 100 YC companies completed with persistent outputs
  • Demo gallery shows all 100 pre-processed companies
  • Comparison against 2 baselines: template-only + single-search+email, with numbers
  • LangSmith trace gallery with ≥30 agent loops linked
  • Cost vs quality analysis documented: at what point does more reflection stop improving

Plus the 12 universal DoD blocks.

License

MIT.

Ver o original no GitHub

Bom para

Relacionados