--- title: Introducing Semantic Operator: Governed Data Access for... description: Kubeflow has launched Semantic Operator, a Kubernetes operator that gives AI agents governed access to business data instead of letting language models write... canonical: https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Semantic Operator: Governed Data Access for AI Agents | daily.dev og:description: Kubeflow has launched Semantic Operator, a Kubernetes operator that gives AI agents governed access to business data instead of letting language models write... og:url: https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr og:image: https://api.daily.dev/og/posts/Ktq7avKBr.png og:image:alt: Introducing Semantic Operator: Governed Data Access for AI Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Semantic Operator: Governed Data Access for AI Agents **[Kubeflow](https://daily.dev/sources/kubeflow)** · 11 min read · 0 upvotes · 0 comments ## Summary Kubeflow has launched Semantic Operator, a Kubernetes operator that gives AI agents governed access to business data instead of letting language models write SQL directly. Data teams define certified metrics once using an Apache Ossie model, and agents request metrics through the Model Context Protocol. Semantic Operator validates the model, applies governance before execution, and compiles one deterministic SQL statement that runs on StarRocks or Trino. The language model never writes SQL itself. It includes an ossiectl command to bootstrap semantic models from existing database schemas, enriched with metadata from tools like DataHub and catalogs like Apache Polaris. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Semantic Operator prevent AI agents from writing incorrect SQL against a database? Semantic Operator never lets the language model write SQL. Instead, agents request certified metrics and dimensions through the Model Context Protocol, governance rules run before query planning, and a deterministic planner compiles one SQL statement from the certified Apache Ossie model definitions, then executes it on StarRocks or Trino. _Teams wiring AI agents to analytical databases can track governance patterns like this on daily.dev._ ### What query engines does Kubeflow Semantic Operator support? Semantic Operator supports StarRocks and Trino, both of which share the same logical planner with engine-specific dialects and clients handling SQL syntax, connectivity, and schema inspection. Adding a new engine only requires building a dialect and a client, since the semantic model, governance rules, and planner stay unchanged. _Developers evaluating query engines for agent-facing data access can follow updates like this on daily.dev._ ### What is Apache Ossie and how does it relate to AI agent data access? Apache Ossie (incubating) is a vendor-neutral specification for semantic models that describes datasets, fields, relationships, metrics, and AI context in a portable format. Kubeflow's Semantic Operator implements this specification as a Kubernetes operator, validating Ossie-based SemanticModel resources against live schemas and serving certified concepts to AI agents via MCP, REST, and governed SQL views. _Anyone standardizing semantic layers across data platforms can keep tabs on specs like Apache Ossie via daily.dev._ ## Similar posts on daily.dev - [Expanded semantic model support in Knowledge Catalog](https://daily.dev/posts/expanded-semantic-model-support-in-knowledge-catalog-qap7apeat) · Google Cloud · 1 upvotes · 0 comments - [Oracle adds a semantic layer to ground AI agents in the business context](https://daily.dev/posts/oracle-adds-a-semantic-layer-to-ground-ai-agents-in-the-business-context-wbi7iqqrm) · InfoWorld · 0 upvotes · 0 comments - [Beyond SQL Generation: How to Teach Agents What Your Database Means](https://daily.dev/posts/beyond-sql-generation-how-to-teach-agents-what-your-database-means-ngei2x7no) · Codemotion · 0 upvotes · 0 comments - [Context, Semantics, and Ontology: A Primer for the Agentic Era](https://daily.dev/posts/context-semantics-and-ontology-a-primer-for-the-agentic-era-kwvutpnte) · MotherDuck · 6 upvotes · 0 comments - [The New Role of Data Teams in the Agentic Analytics Era](https://daily.dev/posts/the-new-role-of-data-teams-in-the-agentic-analytics-era-glcgyclom) · JetBrains · 1 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Semantic Operator: Governed Data Access for AI Agents","url":"https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr"},"datePublished":"2026-10-30T00:26:40.751Z","dateModified":"2026-10-30T00:27:08.382Z","description":"Kubeflow has launched Semantic Operator, a Kubernetes operator that gives AI agents governed access to business data instead of letting language models write...","image":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","thumbnailUrl":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","isAccessibleForFree":true,"articleSection":"Kubeflow","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Kubeflow","logo":"https://media.daily.dev/image/upload/s--kSOGBli9--/f_auto/v1743318307/logos/kubeflow","url":"https://daily.dev/sources/kubeflow"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,mcp","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Kubeflow","item":"https://daily.dev/sources/kubeflow"},{"@type":"ListItem","position":3,"name":"Introducing Semantic Operator: Governed Data Access for AI Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-semantic-operator-governed-data-access-for-ai-agents-ktq7avkbr#faq","mainEntity":[{"@type":"Question","name":"How does Semantic Operator prevent AI agents from writing incorrect SQL against a database?","acceptedAnswer":{"@type":"Answer","text":"Semantic Operator never lets the language model write SQL. Instead, agents request certified metrics and dimensions through the Model Context Protocol, governance rules run before query planning, and a deterministic planner compiles one SQL statement from the certified Apache Ossie model definitions, then executes it on StarRocks or Trino. Teams wiring AI agents to analytical databases can track governance patterns like this on daily.dev."}},{"@type":"Question","name":"What query engines does Kubeflow Semantic Operator support?","acceptedAnswer":{"@type":"Answer","text":"Semantic Operator supports StarRocks and Trino, both of which share the same logical planner with engine-specific dialects and clients handling SQL syntax, connectivity, and schema inspection. Adding a new engine only requires building a dialect and a client, since the semantic model, governance rules, and planner stay unchanged. Developers evaluating query engines for agent-facing data access can follow updates like this on daily.dev."}},{"@type":"Question","name":"What is Apache Ossie and how does it relate to AI agent data access?","acceptedAnswer":{"@type":"Answer","text":"Apache Ossie (incubating) is a vendor-neutral specification for semantic models that describes datasets, fields, relationships, metrics, and AI context in a portable format. Kubeflow's Semantic Operator implements this specification as a Kubernetes operator, validating Ossie-based SemanticModel resources against live schemas and serving certified concepts to AI agents via MCP, REST, and governed SQL views. Anyone standardizing semantic layers across data platforms can keep tabs on specs like Apache Ossie via daily.dev."}}]} ```