Vertex-AI-Notizen für B2B SaaS: Sales-FAQ und Support-Historie trennen

In B2B SaaS wirkt jedes Dokument wie nützlicher KI-Kontext: Sales-FAQ, Help Center, Support-Tickets, Deal-Notizen, Roadmap und Slack-Antworten. Wenn Kundennamen, Verträge, Incidents und unveröffentlichte Features im selben Index landen, wird die FAQ zum Leck.

Dieser Artikel nutzt Claude Code, um vor der Implementierung eine Vertex-AI-Integrationsnotiz zu erstellen. Ziel ist die Trennung von Sales-FAQ und Support-Historie, weniger Unsicherheit vor dem Kauf und Schutz von Kundendaten.

Kernaussagen

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• Humans decide customer names, contracts, incidents, unpublished features, legal wording, and pricing answers.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

Wo SaaS-KI-FAQ-Projekte scheitern

Beginnen Sie mit vier Gruppen: öffentliche Sales-FAQ, Support-FAQ, interne Prüfung und nicht an KI senden. Vertex AI RAG, Grounding, Agent-Search-Datastores und Safety Filters helfen bei fundierten Antworten, entscheiden aber nicht, welche SaaS-Daten öffentlich geeignet sind.

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

Ablauf: Daten vor Vertex AI trennen

Beginnen Sie mit vier Gruppen: öffentliche Sales-FAQ, Support-FAQ, interne Prüfung und nicht an KI senden. Vertex AI RAG, Grounding, Agent-Search-Datastores und Safety Filters helfen bei fundierten Antworten, entscheiden aber nicht, welche SaaS-Daten öffentlich geeignet sind.

| 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 |

Was Claude Code tut und was Menschen entscheiden

Beginnen Sie mit vier Gruppen: öffentliche Sales-FAQ, Support-FAQ, interne Prüfung und nicht an KI senden. Vertex AI RAG, Grounding, Agent-Search-Datastores und Safety Filters helfen bei fundierten Antworten, entscheiden aber nicht, welche SaaS-Daten öffentlich geeignet sind.

3 Use Cases

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.

Kopierbarer Prompt

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/.

Prüfcode

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 lässt falsche Daten richtig klingen

Beginnen Sie mit vier Gruppen: öffentliche Sales-FAQ, Support-FAQ, interne Prüfung und nicht an KI senden. Vertex AI RAG, Grounding, Agent-Search-Datastores und Safety Filters helfen bei fundierten Antworten, entscheiden aber nicht, welche SaaS-Daten öffentlich geeignet sind.

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.

Mit uns sprechen

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

Was ich geprüft habe

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.