Catatan Vertex AI untuk B2B SaaS: pisahkan FAQ sales dan riwayat support

Dalam B2B SaaS, semua dokumen terlihat seperti konteks AI yang berguna: FAQ sales, help center, tiket support, catatan sales, roadmap, dan jawaban Slack. Jika nama pelanggan, kontrak, insiden, dan fitur belum publik masuk indeks yang sama, FAQ menjadi jalur kebocoran.

Artikel ini memakai Claude Code untuk menyiapkan catatan integrasi Vertex AI sebelum implementasi. Tujuannya memisahkan FAQ sales dari riwayat support, mengurangi keraguan pra-penjualan, dan menjaga data pelanggan dari konteks AI yang terlalu luas.

Poin utama

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• Humans decide customer names, contracts, incidents, unpublished features, legal wording, and pricing answers.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

Di mana proyek FAQ AI SaaS gagal

Mulailah dari empat bucket: FAQ sales publik, FAQ support, review internal, dan jangan kirim ke AI. Vertex AI RAG, Grounding, data store Agent Search, dan safety filters membantu jawaban berbasis sumber, tetapi tidak menentukan data SaaS mana yang aman untuk jawaban publik.

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

Alur: pisahkan data sebelum Vertex AI

Mulailah dari empat bucket: FAQ sales publik, FAQ support, review internal, dan jangan kirim ke AI. Vertex AI RAG, Grounding, data store Agent Search, dan safety filters membantu jawaban berbasis sumber, tetapi tidak menentukan data SaaS mana yang aman untuk jawaban publik.

| 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 |

Apa yang dilakukan Claude Code dan apa yang diputuskan manusia

Mulailah dari empat bucket: FAQ sales publik, FAQ support, review internal, dan jangan kirim ke AI. Vertex AI RAG, Grounding, data store Agent Search, dan safety filters membantu jawaban berbasis sumber, tetapi tidak menentukan data SaaS mana yang aman untuk jawaban publik.

3 Use case

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 siap salin

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/.

Kode pemeriksaan

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 membuat data salah terdengar benar

Mulailah dari empat bucket: FAQ sales publik, FAQ support, review internal, dan jangan kirim ke AI. Vertex AI RAG, Grounding, data store Agent Search, dan safety filters membantu jawaban berbasis sumber, tetapi tidak menentukan data SaaS mana yang aman untuk jawaban publik.

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.

Bicara dengan kami

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

Yang dicek

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.