{"id":16851,"date":"2026-06-15T21:01:58","date_gmt":"2026-06-15T12:01:58","guid":{"rendered":"https:\/\/m365jp.net\/?p=16851"},"modified":"2026-06-15T21:04:11","modified_gmt":"2026-06-15T12:04:11","slug":"mc1391881-microsoft-power-automate-connect-to-local-ai-models-from-desktop-flows","status":"publish","type":"post","link":"https:\/\/m365jp.net\/index.php\/2026-06-15-mc1391881-microsoft-power-automate-connect-to-local-ai-models-from-desktop-flows","title":{"rendered":"MC1391881 | Microsoft Power Automate – Connect to local AI models from desktop flows"},"content":{"rendered":"
\n
\n
\n\n\n\n
MC1391881 | Microsoft Power Automate – Connect to local AI models from desktop flows<\/th>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n\n\n\n\n\n\n\n\n
Classification<\/th>\nstayInformed<\/td>\n<\/tr>\n
Last Updated<\/th>\n06\/15\/2026 11:17:45<\/td>\n<\/tr>\n
Start Time<\/th>\n06\/15\/2026 11:16:23<\/td>\n<\/tr>\n
End Time<\/th>\n07\/15\/2026 11:16:23<\/td>\n<\/tr>\n
Message Content<\/th>\nWe are announcing the ability to connect to local AI models from desktop flows in Microsoft Power Automate. This feature will reach public preview on June 30, 2026.<\/p>\n

How does this affect me?<\/b><\/p>\n

You can now add AI to your desktop flows without sending data outside your environment. By running models locally, you’ll keep control of your data, meet privacy standards, and cut dependency on external services.<\/p>\n

Users can connect to a locally hosted model by providing the endpoint URL, defining system and user prompts, and optionally include files as input. The action returns the model’s response as an output variable, which can be used in subsequent steps of the desktop flow to drive decisions and enrich automation scenarios.<\/p>\n

This capability supports models exposed through APIs compatible with the OpenAI standard, enabling integration with commonly used local model providers such as Ollama, vLLM, and LM Studio.<\/p>\n

What action do I need to take?<\/b><\/p>\n

This message is for awareness, and no action is required.<\/p>\n

If you would like more information on this feature, please visit, please visit Connect to local AI models from desktop flows<\/a>.<\/td>\n<\/tr>\n

Machine Translation<\/th>\nMicrosoft Power Automate\u306e\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u30d5\u30ed\u30fc\u304b\u3089\u30ed\u30fc\u30ab\u30ebAI\u30e2\u30c7\u30eb\u306b\u63a5\u7d9a\u3067\u304d\u308b\u6a5f\u80fd\u3092\u767a\u8868\u3057\u307e\u3059\u3002\u3053\u306e\u7279\u96c6\u306f2026\u5e746\u670830\u65e5\u306b\u4e00\u822c\u516c\u958b\u3055\u308c\u307e\u3059\u3002<\/p>\n

\u3053\u308c\u304c\u79c1\u306b\u3069\u3046\u5f71\u97ff\u3059\u308b\u306e\u3067\u3057\u3087\u3046\u304b?<\/b>
\u4eca\u3067\u306f\u3001\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u30d5\u30ed\u30fc\u306bAI\u3092\u8ffd\u52a0\u3067\u304d\u3001\u74b0\u5883\u5916\u306b\u30c7\u30fc\u30bf\u3092\u9001\u308b\u5fc5\u8981\u304c\u306a\u304f\u306a\u308a\u307e\u3059\u3002\u30ed\u30fc\u30ab\u30eb\u3067\u30e2\u30c7\u30eb\u3092\u904b\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u30c7\u30fc\u30bf\u306e\u7ba1\u7406\u3092\u7d9a\u3051\u3001\u30d7\u30e9\u30a4\u30d0\u30b7\u30fc\u57fa\u6e96\u3092\u6e80\u305f\u3057\u3001\u5916\u90e8\u30b5\u30fc\u30d3\u30b9\u3078\u306e\u4f9d\u5b58\u3092\u6e1b\u3089\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n

\u30e6\u30fc\u30b6\u30fc\u306f\u30a8\u30f3\u30c9\u30dd\u30a4\u30f3\u30c8\u306eURL\u3092\u63d0\u4f9b\u3057\u3001\u30b7\u30b9\u30c6\u30e0\u3084\u30e6\u30fc\u30b6\u30fc\u30d7\u30ed\u30f3\u30d7\u30c8\u3092\u5b9a\u7fa9\u3057\u3001\u30aa\u30d7\u30b7\u30e7\u30f3\u3067\u5165\u529b\u3068\u3057\u3066\u30d5\u30a1\u30a4\u30eb\u3092\u542b\u3081\u308b\u3053\u3068\u3067\u30ed\u30fc\u30ab\u30eb\u30db\u30b9\u30c8\u30e2\u30c7\u30eb\u306b\u63a5\u7d9a\u3067\u304d\u307e\u3059\u3002\u3053\u306e\u30a2\u30af\u30b7\u30e7\u30f3\u306f\u30e2\u30c7\u30eb\u306e\u5fdc\u7b54\u3092\u51fa\u529b\u5909\u6570\u3068\u3057\u3066\u8fd4\u3057\u3001\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u30d5\u30ed\u30fc\u306e\u5f8c\u7d9a\u306e\u30b9\u30c6\u30c3\u30d7\u3067\u610f\u601d\u6c7a\u5b9a\u3092\u63a8\u9032\u3057\u3001\u81ea\u52d5\u5316\u30b7\u30ca\u30ea\u30aa\u3092\u8c4a\u304b\u306b\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n

\u3053\u306e\u6a5f\u80fd\u306fOpenAI\u6a19\u6e96\u3068\u4e92\u63db\u6027\u306e\u3042\u308bAPI\u3092\u901a\u3058\u3066\u516c\u958b\u3055\u308c\u305f\u30e2\u30c7\u30eb\u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3001Ollama\u3001vLLM\u3001LM Studio\u306a\u3069\u306e\u4e00\u822c\u7684\u306a\u30ed\u30fc\u30ab\u30eb\u30e2\u30c7\u30eb\u30d7\u30ed\u30d0\u30a4\u30c0\u30fc\u3068\u306e\u7d71\u5408\u3092\u53ef\u80fd\u306b\u3057\u307e\u3059\u3002<\/p>\n

\u3069\u3093\u306a\u5bfe\u5fdc\u3092\u53d6\u308c\u3070\u3044\u3044\u306e\u3067\u3057\u3087\u3046\u304b?<\/b>
\u3053\u306e\u30e1\u30c3\u30bb\u30fc\u30b8\u306f\u610f\u8b58\u5411\u4e0a\u306e\u305f\u3081\u306e\u3082\u306e\u3067\u3042\u308a\u3001\u884c\u52d5\u306f\u5fc5\u8981\u3042\u308a\u307e\u305b\u3093\u3002<\/p>\n

\u3053\u306e\u6a5f\u80fd\u306b\u3064\u3044\u3066\u3055\u3089\u306b\u8a73\u3057\u304f\u77e5\u308a\u305f\u3044\u65b9\u306f\u3001\u300c \u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u30d5\u30ed\u30fc\u304b\u3089\u30ed\u30fc\u30ab\u30ebAI\u30e2\u30c7\u30eb\u306b\u63a5\u7d9a\u300d<\/a>\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002<\/td>\n<\/tr>\n<\/tbody>\n<\/table><\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

MC1391881 | Microsoft Power Automate – Connect to local AI models from desktop flows Classification stay […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-16851","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/posts\/16851","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/comments?post=16851"}],"version-history":[{"count":0,"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/posts\/16851\/revisions"}],"wp:attachment":[{"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/media?parent=16851"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/categories?post=16851"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/m365jp.net\/index.php\/wp-json\/wp\/v2\/tags?post=16851"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}