Notas de Vertex AI para B2B SaaS: separar FAQ comercial e histórico de suporte

Em B2B SaaS, tudo parece contexto útil para IA: FAQ comercial, central de ajuda, tickets, notas de vendas, roadmap e respostas do Slack. Se nomes de clientes, contratos, incidentes e funções não publicadas entram no mesmo índice, a FAQ vira caminho de vazamento.

Este artigo usa Claude Code para preparar uma nota de integração com Vertex AI antes da implementação. O objetivo é separar FAQ comercial e histórico de suporte, reduzir dúvidas de pré-venda e proteger dados de clientes.

Pontos principais

• Keep sales FAQ, help content, support history, deal notes, and roadmap data in separate buckets.

• Use Vertex AI RAG, Grounding, Agent Search, and safety filters after data boundaries are clear.

• Claude Code drafts classification tables, test questions, prompts, and operations notes.

• Humans decide customer names, contracts, incidents, unpublished features, legal wording, and pricing answers.

• Send implementation-heavy readers to training because every SaaS has different data rules.

Onde projetos de FAQ com IA em SaaS falham

Comece com quatro grupos: FAQ comercial pública, FAQ de suporte, revisão interna e não enviar para IA. Vertex AI RAG, Grounding, data stores do Agent Search e safety filters ajudam nas respostas com base, mas não decidem quais dados SaaS são seguros para respostas públicas.

Official references: RAG Engine, Grounding overview, Grounding with Google Search, Agent Search data stores, Safety filters, and Responsible AI.

Fluxo: separar dados antes do Vertex AI

Comece com quatro grupos: FAQ comercial pública, FAQ de suporte, revisão interna e não enviar para IA. Vertex AI RAG, Grounding, data stores do Agent Search e safety filters ajudam nas respostas com base, mas não decidem quais dados SaaS são seguros para respostas públicas.

| Source | AI use | Human review |

| --- | --- | --- |

| Sales FAQ | public features, public pricing, buying questions | legal wording and pricing examples |

| Help center | operations, settings, roles, errors | old UI and deprecated features |

| Support history | anonymized patterns and frequent errors | customer names, contracts, incidents |

| Deal notes | usually no direct AI use | budget, discount, roadmap, buyer name |

O que Claude Code faz e o que humanos decidem

Comece com quatro grupos: FAQ comercial pública, FAQ de suporte, revisão interna e não enviar para IA. Vertex AI RAG, Grounding, data stores do Agent Search e safety filters ajudam nas respostas com base, mas não decidem quais dados SaaS são seguros para respostas públicas.

3 casos de uso

Use case 1: Split sales FAQ and support history

• Input: public FAQ, help articles, support CSV columns, ticket tags, pre-sales questions.

• Output: four-bucket table: sales FAQ, support FAQ, internal review, do-not-send-to-AI.

• Human review: check customer names, contracts, incident history, unpublished features, and special pricing.

Use case 2: Build test questions before Vertex AI

• Input: buyer persona, pricing page, help articles, prohibited answers, escalation rules.

• Output: allowed questions, handoff questions, and questions requiring source links.

• Human review: decide boundaries for pricing, contracts, security, incidents, cancellation, and custom requests.

Use case 3: Create operations notes for wrong answers

• Input: wrong answers, ticket logs, support corrections, FAQ update history.

• Output: issue class, data source to fix, retest question, and approver.

• Human review: legal wording, refund terms, incident explanations, customer impact, and release timing.

Prompt para copiar

Create a Vertex AI integration note for a B2B SaaS. Goal: separate sales FAQ from support history and avoid sending customer data into broad AI context. Create four buckets, twenty test questions, handoff rules, source-link rules, and operations notes. Do not paste real customer values. Main CTA: /training/.

Código de verificação

const faqCandidates = [{ source: 'support_history', title: 'Client incident response', bucket: 'sales_faq', fields: ['customerName', 'incidentId', 'contractNote'] }];

const sensitiveHints = [/customer/i, /contract/i, /incident/i, /discount/i, /account/i];

const findings = faqCandidates.flatMap((item) => {

  const sensitiveFields = item.fields.filter((field) => sensitiveHints.some((pattern) => pattern.test(field)));

  return item.bucket === 'sales_faq' && sensitiveFields.length ? [{ title: item.title, issue: sensitiveFields.join(', ') }] : [];

});

console.table(findings);

if (findings.length) process.exitCode = 1;

Pitfall: RAG faz dados errados parecerem corretos

Comece com quatro grupos: FAQ comercial pública, FAQ de suporte, revisão interna e não enviar para IA. Vertex AI RAG, Grounding, data stores do Agent Search e safety filters ajudam nas respostas com base, mas não decidem quais dados SaaS são seguros para respostas públicas.

Cause: RAG brings answers closer to the indexed data. If the indexed data is wrong for sales use, the answer becomes confidently wrong or unsafe. Fix: split data before ingestion, use anonymized support patterns, and keep contracts, incidents, and roadmap notes out of public FAQ context.

FAQ

Q. What should come first? A. A data classification table, not a model setting.

Q. Should all support history be removed? A. No. Patterns and tags can help, but customer-specific details need separation.

Q. Why training? A. Vertex AI, Agent Search, RAG, data boundaries, and security review differ by SaaS.

Fale conosco

ClaudeCodeLab training can help create FAQ buckets, test questions, and operations notes before Vertex AI or Agent Search implementation.

O que foi verificado

This article checks frontmatter, official links, three use cases, input-output-human review labels, code fences, and the /training/ CTA. The JavaScript sample detects customer, contract, and incident fields mixed into sales FAQ candidates.