Notas de Vertex AI para B2B SaaS: separar FAQ comercial e historial de soporte

En B2B SaaS, todo parece contexto útil para IA: FAQ comercial, centro de ayuda, tickets, notas de ventas, roadmap y respuestas de Slack. Si nombres de clientes, contratos, incidentes y funciones no publicadas entran al mismo índice, la FAQ se vuelve una vía de fuga.

Este artículo usa Claude Code para preparar una nota de integración con Vertex AI antes de implementar. El objetivo es separar FAQ comercial e historial de soporte, reducir dudas de preventa y no entregar datos de clientes a un contexto amplio de IA.

Puntos clave

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• Humans decide customer names, contracts, incidents, unpublished features, legal wording, and pricing answers.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

Dónde fallan los proyectos de FAQ con IA en SaaS

Empieza con cuatro grupos: FAQ comercial pública, FAQ de soporte, revisión interna y no enviar a IA. Vertex AI RAG, Grounding, data stores de Agent Search y safety filters ayudan con respuestas fundamentadas, pero no deciden qué datos SaaS son seguros para respuestas públicas o de preventa.

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

Flujo: separar datos antes de Vertex AI

Empieza con cuatro grupos: FAQ comercial pública, FAQ de soporte, revisión interna y no enviar a IA. Vertex AI RAG, Grounding, data stores de Agent Search y safety filters ayudan con respuestas fundamentadas, pero no deciden qué datos SaaS son seguros para respuestas públicas o de preventa.

| 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 |

Qué hace Claude Code y qué decide una persona

Empieza con cuatro grupos: FAQ comercial pública, FAQ de soporte, revisión interna y no enviar a IA. Vertex AI RAG, Grounding, data stores de Agent Search y safety filters ayudan con respuestas fundamentadas, pero no deciden qué datos SaaS son seguros para respuestas públicas o de preventa.

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 revisión

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 hace que datos incorrectos suenen correctos

Empieza con cuatro grupos: FAQ comercial pública, FAQ de soporte, revisión interna y no enviar a IA. Vertex AI RAG, Grounding, data stores de Agent Search y safety filters ayudan con respuestas fundamentadas, pero no deciden qué datos SaaS son seguros para respuestas públicas o de preventa.

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.

Hablar con nosotros

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

Lo que comprobé

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.