My App
AI Support

Ingestion and Evaluation

Recommended metadata and evaluation checklist for the Lexul support AI agent.

Metadata fieldRecommended value
productLexul Field Service
content_typecustomer_support_chatbot_training_record
audienceLexul customer support chatbot, support team, onboarding team
chunkingOne sub-feature training card per chunk; preserve record_id and source_urls.
retrieval_priorityPrefer exact feature/sub_feature match; then alias/sample utterance match; then source URL match.
answer_styleConcise, workflow-specific, ask one clarifying question when needed, include guardrail if relevant.
escalation_behaviorEscalate sync/data integrity, accounting advice, permission/security changes, custom development, unsupported roadmap requests.

Appendix C: Agent evaluation checklist

  • Can the agent answer a setup question using the correct feature record?
  • Can the agent choose between related features such as contracts, recurring work orders, and summary invoicing?
  • Can the agent ask only one focused clarification question when QuickBooks version, user role, customer/asset structure, or billing workflow matters?
  • Can the agent avoid unsupported claims and escalate custom-development, accounting, sync, and data-integrity issues?
  • Can the agent cite or surface the relevant Lexul source URL when responding?

On this page