{"componentChunkName":"component---src-templates-simple-markdown-js","path":"/process-intelligence-apis/knowledge-model-api/beta-features/ai/semantic/","matchPath":"","result":{"data":{"markdownRemark":{"html":"<h1 style=\"position:relative;\"><a href=\"#semantic-extensions-of-knowledge-model-api-enabling-ai-agents\" aria-label=\"semantic extensions of knowledge model api enabling ai agents permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"semantic-extensions-of-knowledge-model-api-enabling-ai-agents\"></div>Semantic extensions of Knowledge Model API enabling AI Agents</h1>\n<p>Building up semantic understanding of Celonis data in a specific business context (Knowledge Model - KM) so that third-party (3P) AI Agents can figure out the right way to query Celonis data.\nTherefore, the Knowledge Model API is being enhanced to provide:</p>\n<ul>\n<li>\n<strong>Structure discovery</strong>\n: A new endpoint focusing on the KM data structures (including schema and description).\n</li>\n<li>\n<strong>Content discovery</strong>\n: A new endpoint providing statistical profiling of the data contents per KM record.\n</li>\n<li>\n<strong>Relationship discovery</strong>\n: To be added in the future.\nFuture extensions will include the supply of the necessary process context to the 3P AI agents to power business process automation.\n<h2 style=\"position:relative;\"><a href=\"#3p-ai-agent-enablement-beta-program\" aria-label=\"3p ai agent enablement beta program permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"3p-ai-agent-enablement-beta-program\"></div>3P AI Agent Enablement (BETA program) <sup id=\"fnref-1\"><a href=\"#fn-1\" class=\"footnote-ref\">1</a></sup></h2>\n<h3 style=\"position:relative;\"><a href=\"#knowledge-model-semantic-openapi-spec\" aria-label=\"knowledge model semantic openapi spec permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"knowledge-model-semantic-openapi-spec\"></div>Knowledge Model Semantic OpenAPI Spec</h3>\n<p>To retrieve the semantic specification of a Knowledge Model - KM (according to <a href=\"https://spec.openapis.org/oas/latest.html\">Open API Initiative</a>), either in <code class=\"language-text\">json</code> or <code class=\"language-text\">yml</code> format, you need to consume the endpoint:\n<code class=\"language-text\">GET /knowledge-models/{{km-id}}/spec</code>\nYou have the option to select either all KM records (including the <em>auto-generated</em>) or only the <em>curated</em> ones by submitting the parameter <code class=\"language-text\">curated=true</code>.\nThe Knowledge Model semantic metadata, including <strong>schema</strong> and <strong>data descriptions</strong>, are shared with the 3P agent enabling them to understand Celonis context and data.</p>\n<h3 style=\"position:relative;\"><a href=\"#knowledge-model-record-semantic-data-content-statistics\" aria-label=\"knowledge model record semantic data content statistics permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"knowledge-model-record-semantic-data-content-statistics\"></div>Knowledge Model Record Semantic Data Content Statistics</h3>\n<p>To retrieve the Knowledge Model - KM record content statistics, you need to consume the endpoint:\n<code class=\"language-text\">GET /knowledge-models/{{km-id}}/records/{{record-id}}/summary</code>\nThe results contain:</p>\n</li>\n<li>\nThe \n<strong>Schema</strong>\n array\n</li>\n<li>\nThe \n<strong>Data Sample</strong>\n array\n</li>\n<li>\nThe \n<strong>Shape</strong>\n array (number of rows, number of columns\n</li>\n<li>\nThe \n<strong>Column Summary Statistics</strong>\n array including the following metrics for each KM record field (excluding KPIs, flags and augmented attributes):\n<ul>\n<li>\n<code class=\"language-text\">count</code>\n: Number of non-null values (applicable to all field types)\n</li>\n<li>\n<code class=\"language-text\">unique</code>\n: Number of unique non-null values (applicable only to strings &#x26; timestamps) \n</li>\n<li>\n<code class=\"language-text\">top</code>\n: Most frequent value (applicable only to strings &#x26; timestamps)\n</li>\n<li>\n<code class=\"language-text\">freq</code>\n: Frequency of the most frequent value (applicable only to strings &#x26; timestamps)\n</li>\n<li>\n<code class=\"language-text\">mean</code>\n: Mean of the values (applicable only to numeric fields)\n</li>\n<li>\n<code class=\"language-text\">std</code>\n: Standard deviation of the values (applicable only to numeric fields)\n</li>\n<li>\n<code class=\"language-text\">min</code>\n: Minimum value (applicable only to numeric fields)\n</li>\n<li>\n<code class=\"language-text\">max</code>\n: Maximum value (applicable only to numeric fields)        \n</li>\n<li>\n<code class=\"language-text\">25% percentile</code>\n (applicable only to numeric fields)\n</li>\n<li>\n<code class=\"language-text\">50% percentile</code>\n (applicable only to numeric fields)\n</li>\n<li>\n<code class=\"language-text\">75% percentile</code>\n (applicable only to numeric fields)\nThe optional parameters controlling which data will be analyzed are:\n</li>\n</ul>\n</li>\n<li>\n<code class=\"language-text\">filters</code>\n: The filters to be applied on data contents (column statistic profiling may differ significantly depending on the applied filter); default \n<code class=\"language-text\">none</code>\n</li>\n<li>\n<code class=\"language-text\">fields</code>\n: The fields whose contents will be analyzed (if omitted all record fields will be statistically profiled); default \n<code class=\"language-text\">all</code>\n</li>\n<li>\n<code class=\"language-text\">excludeFields</code>\n: The fields to exclude from the statistical analysis; default \n<code class=\"language-text\">none</code>\n</li>\n<li>\n<code class=\"language-text\">sampleSize</code>\n: For requesting a specific number of rows for the data; default \n<code class=\"language-text\">10</code>\n<h3 style=\"position:relative;\"><a href=\"#knowledge-model-semantic-query\" aria-label=\"knowledge model semantic query permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"knowledge-model-semantic-query\"></div>Knowledge Model Semantic Query</h3>\n<p>To query the Knowledge Model, you need to consume the endpoint:\n<code class=\"language-text\">GET /knowledge-models/{{km-id}}/query</code>. The parameters of <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getKnowledgeModelQueryResult/\">/query</a> are similar to <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getRecordDataResult/\">/data</a> endpoint with the difference that we have an optional parameter called <code class=\"language-text\">kpis</code> to retrieve the KPIs of the knowledge model.\nThe response format is structured as a json object compared to the array of name and value. You can refer to the <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getKnowledgeModelQueryResult/\">/query</a> endpoint for more information.</p>\n<h3 style=\"position:relative;\"><a href=\"#knowledge-model-record-semantic-query\" aria-label=\"knowledge model record semantic query permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"knowledge-model-record-semantic-query\"></div>Knowledge Model Record Semantic Query</h3>\n<p>To query the Knowledge Model - KM record data, you need to consume the endpoint:\n<code class=\"language-text\">GET /knowledge-models/{{km-id}}/records/{{record-id}}/query</code>\nThe same parameters as the <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getRecordDataResult/\">/data</a> endpoint are supported with the only difference that <code class=\"language-text\">fields</code> is optional. If omitted, all KM record fields are included.\nThe response format is structured as a json object compared to the array of name. An example is provided here <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getRecordQueryResult/\">/record/query</a>.</p>\n<h3 style=\"position:relative;\"><a href=\"#fuzzy-search\" aria-label=\"fuzzy search permalink\" class=\"anchor before\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"16\" version=\"1.1\" viewBox=\"0 0 16 16\" width=\"16\"><path fill-rule=\"evenodd\" d=\"M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z\"></path></svg></a><div class=\"hidden-anchor\" id=\"fuzzy-search\"></div>Fuzzy Search</h3>\n<p>This feature fuzzy string search try to find the best match in a string.\nIt is found in the following endpoints: <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getKnowledgeModelQueryResult/\">/query</a>, <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getRecordQueryResult/\">/record/query</a> and <a href=\"https://developer.celonis.com/process-intelligence-apis/knowledge-model-api/api-reference/openapi/reference/operation/getRecordDataResult/\">/data</a>.</p>\n</li>\n</ul>\n<div class=\"footnotes\">\n<hr>\n<ol>\n<li id=\"fn-1\">\n<p>Please contact your Celonis account team if you want to join the 3P AI Agent Enablement Beta program.</p>\n<a href=\"#fnref-1\" class=\"footnote-backref\">↩</a>\n</li>\n</ol>\n</div>","headings":[{"value":"Semantic extensions of Knowledge Model API enabling AI Agents","depth":1},{"value":"3P AI Agent Enablement (BETA program) ","depth":2},{"value":"Knowledge Model Semantic OpenAPI Spec","depth":3},{"value":"Knowledge Model Record Semantic Data Content Statistics","depth":3},{"value":"Knowledge Model Semantic Query","depth":3},{"value":"Knowledge Model Record Semantic Query","depth":3},{"value":"Fuzzy Search","depth":3}]},"contentItem":{"data":{"lastModified":"2025-10-08T17:14:46.000Z","enableToc":null,"disableLastModified":null,"tocMaxDepth":null,"requestLogin":false}},"siteConfig":{"enableToc":false,"disableLastModified":false,"tocMaxDepth":4}},"pageContext":{"matchPath":"","id":"8ae71e63-54ff-5025-b0f1-c3cf8a142811__redocly content/process-intelligence-apis/knowledge-model-api/beta-features/ai/semantic/","seo":{"title":"Semantic extensions of Knowledge Model API enabling AI Agents","description":null,"image":"","keywords":null,"jsonLd":null,"lang":null,"siteUrl":null},"pageId":"process-intelligence-apis/knowledge-model-api/beta-features/ai/semantic.md","pageBaseUrl":"/process-intelligence-apis/knowledge-model-api/beta-features/ai/semantic","type":"markdown","toc":{"enable":true,"maxDepth":4,"headings":[{"depth":1,"value":"Semantic extensions of Knowledge Model API enabling AI Agents","id":"semantic-extensions-of-knowledge-model-api-enabling-ai-agents"},{"depth":2,"value":"3P AI Agent Enablement (BETA program) ","id":"3p-ai-agent-enablement-beta-program"},{"depth":3,"value":"Knowledge Model Semantic OpenAPI Spec","id":"knowledge-model-semantic-openapi-spec"},{"depth":3,"value":"Knowledge Model Record Semantic Data Content Statistics","id":"knowledge-model-record-semantic-data-content-statistics"},{"depth":3,"value":"Knowledge Model Semantic Query","id":"knowledge-model-semantic-query"},{"depth":3,"value":"Knowledge Model Record Semantic Query","id":"knowledge-model-record-semantic-query"},{"depth":3,"value":"Fuzzy Search","id":"fuzzy-search"}]},"data":{"title":""},"catalogInfo":null,"link":"/process-intelligence-apis/knowledge-model-api/beta-features/ai/semantic/","sidebarName":"celonis","isLanding":false,"showPrevButton":null,"showNextButton":null,"apiVersions":null,"apiVersionId":null,"isDefaultApiVersion":null}},"staticQueryHashes":["1123603147","1302185487","1344209882","1398840060","1520077861","1975142765","2667623876","2950305614","3240152602","3743992808","561138138"]}