{"title":"Transparency note: Semantic Metadata Search in Business Central","url":"https://jonas-paprotka.de/docs/dev-itpro/ai/transparency-note-semantic-metadata-search/","by":"JOP-AL","license":"Copyright (c) Microsoft Corporation. CC BY 4.0, https://creativecommons.org/licenses/by/4.0/; code samples MIT. From https://learn.microsoft.com/en-us/dynamics365/business-central/dev-itpro/ai/transparency-note-semantic-metadata-search, MicrosoftDocs/dynamics365smb-devitpro-pb at 828b6ee (2026-11-19). Changed: includes filled in, links to this site, and for agents shortened without dropping a fact.","credit":"Microsoft Corporation, CC BY 4.0","origin":"https://learn.microsoft.com/en-us/dynamics365/business-central/dev-itpro/ai/transparency-note-semantic-metadata-search","source":{"name":"Business Central developer and IT pro docs","repo":"https://github.com/MicrosoftDocs/dynamics365smb-devitpro-pb","commit":"828b6ee72fcd75755627cd6011f3d20899217ab2","date":"2026-11-19"},"checked":"2026-11-19","description":"Semantic Metadata Search helps you build safer, adaptable AI features. Learn how to use the toolkit and boost productivity.","date":"2026-10-02","meta":{"topic":"faq"},"outline":[{"level":1,"title":"Transparency note: Semantic Metadata Search in Business Central","slug":"transparency-note-semantic-metadata-search-in-business-central","at":0,"chars":3334},{"level":2,"title":"What is a Transparency Note?","slug":"what-is-a-transparency-note","at":66,"chars":907},{"level":2,"title":"The basics of Semantic Metadata Search in Business Central","slug":"the-basics-of-semantic-metadata-search-in-business-central","at":973,"chars":887},{"level":3,"title":"Introduction","slug":"introduction","at":1035,"chars":472},{"level":3,"title":"Key terms","slug":"key-terms","at":1507,"chars":353},{"level":2,"title":"Capabilities","slug":"capabilities","at":1860,"chars":664},{"level":3,"title":"System components","slug":"system-components","at":1876,"chars":213},{"level":3,"title":"Use cases","slug":"use-cases","at":2089,"chars":435},{"level":4,"title":"Intended uses","slug":"intended-uses","at":2103,"chars":179},{"level":4,"title":"Considerations when choosing a use case","slug":"considerations-when-choosing-a-use-case","at":2282,"chars":242},{"level":2,"title":"Limitations","slug":"limitations","at":2524,"chars":183},{"level":3,"title":"Mitigations","slug":"mitigations","at":2611,"chars":96},{"level":2,"title":"Evaluation of Semantic Metadata Search in Business Central","slug":"evaluation-of-semantic-metadata-search-in-business-central","at":2707,"chars":233},{"level":2,"title":"Learn more about responsible AI","slug":"learn-more-about-responsible-ai","at":2940,"chars":281},{"level":2,"title":"Related information","slug":"related-information","at":3221,"chars":113}],"text":"# Transparency note: Semantic Metadata Search in Business Central\n## What is a Transparency Note?\nAn AI system includes the technology, the people who use it, the people it affects, and the environment where it's deployed. Creating a system that is fit for its intended purpose requires an understanding of how the technology works, what its capabilities and limitations are, and how to achieve the best performance. Microsoft's Transparency Notes help you learn how our AI technology works, what choices system owners can make to influence system performance and behavior, and why it's important to consider the whole system, including the technology, people, and environment. Use Transparency Notes when you develop or deploy your own system, or share them with people who use or are affected by your system.\nMicrosoft's Transparency Notes are part of a broader effort at Microsoft to put our AI Principles into practice. See Microsoft AI principles<https://aka.ms/RAI>.\n## The basics of Semantic Metadata Search in Business Central\n### Introduction\nSemantic Metadata Search is an AI-powered capability designed to improve navigation and discoverability in Microsoft Dynamics 365 Business Central. Unlike traditional keyword-based search, it uses semantic similarity to match user queries with metadata entities (such as page captions, descriptions, and additional search terms). This enables users to find relevant pages, reports, and queries even when their wording does not exactly match the metadata.\n### Key terms\nTerminology|Definition\n-|-\nSemantic search|A search technique that uses natural language understanding to match meaning rather than exact keywords.\nMetadata|Descriptive information about application objects such as pages, reports, and queries.\nUI|User Interface where the search feature is integrated, such as Tell Me and Report Explorer.\n## Capabilities\n### System components\n Matches user queries to semantically similar metadata entities.\n Handles synonyms, abbreviations, and non-standard phrasing.\n Integrates into existing UI components for seamless navigation.\n### Use cases\n#### Intended uses\n Help users efficiently locate pages, reports, and queries.\n Reduce reliance on exact keyword matching.\n Enhance user experience with context-aware navigation.\n#### Considerations when choosing a use case\n Metadata Quality: Search accuracy depends on well-maintained metadata (captions, descriptions, additional search terms).\n Scope: Not intended for searching business data or transactional records.\n## Limitations\n Accuracy varies with metadata quality.\n Does not search business data.\n### Mitigations\n Use clear, descriptive queries.\n Maintain accurate metadata for better results\n## Evaluation of Semantic Metadata Search in Business Central\nTested with over 12,000 cases covering synonyms, abbreviations, and semantic variations. Performance measured by accuracy of expected results in the top 3 returned items.\n## Learn more about responsible AI\nMicrosoft AI principles<https://www.microsoft.com/en-us/ai/responsible-ai>\nMicrosoft responsible AI resources<https://www.microsoft.com/en-us/ai/tools-practices>\nMicrosoft Azure Learning courses on responsible AI<https://learn.microsoft.com/ai/>\n## Related information\nConfigure Business Central MCP Server<configure-mcp-server>\ncreate-agent-in-copilot-studio"}