[et_pb_section fb_built=\u201e1\u201c _builder_version=\u201e4.16\u201c custom_padding=\u201e0px||0px||true\u201c da_disable_devices=\u201eoff|off|off\u201c locked=\u201eoff\u201c global_colors_info=\u201c{}\u201c da_is_popup=\u201eoff\u201c da_exit_intent=\u201eoff\u201c da_has_close=\u201eon\u201c da_alt_close=\u201eoff\u201c da_dark_close=\u201eoff\u201c da_not_modal=\u201eon\u201c da_is_singular=\u201eoff\u201c da_with_loader=\u201eoff\u201c da_has_shadow=\u201eon\u201c][et_pb_row _builder_version=\u201e4.27.4\u201c custom_padding=\u201e0px||||false|false\u201c global_colors_info=\u201c{}\u201c][et_pb_column type=\u201e4_4\u201c _builder_version=\u201e4.16\u201c custom_padding=\u201c|||\u201c global_colors_info=\u201c{}\u201c custom_padding__hover=\u201c|||\u201c][et_pb_post_title author=\u201eoff\u201c date=\u201eoff\u201c categories=\u201eoff\u201c comments=\u201eoff\u201c _builder_version=\u201e4.27.4\u201c _module_preset=\u201edefault\u201c title_font=\u201c|800|||||||\u201c global_colors_info=\u201c{}\u201c][\/et_pb_post_title][et_pb_text _builder_version=\u201e4.27.4\u201c header_font=\u201c|700|||||||\u201c header_4_letter_spacing=\u201e12px\u201c module_alignment=\u201ecenter\u201c saved_tabs=\u201eall\u201c locked=\u201eoff\u201c global_colors_info=\u201c{}\u201c]<\/p>\n
Insiders is inten\u00adsi\u00advely engaged with the question of how arti\u00adfi\u00adcial intel\u00adli\u00adgence will work in the future. Instead of relying on a mono\u00adli\u00adthic \u201call-rounder model,\u201d Insiders is deve\u00adlo\u00adping Agentic AI\u2014a network of spe\u00adcia\u00adlized agents that use the appro\u00adpriate tools depending on the process and make decisions inde\u00adpendently. A central component in this deve\u00adlo\u00adp\u00adment is the Model Context Protocol (MCP).<\/p>\n
[\/et_pb_text][et_pb_text _builder_version=\u201e4.27.4\u201c _module_preset=\u201edefault\u201c header_font=\u201c|700|||||||\u201c header_4_letter_spacing=\u201e12px\u201c module_alignment=\u201ecenter\u201c global_colors_info=\u201c{}\u201c]<\/p>\n
<\/p>\n
Until now, every external connection\u2014whether API, database, or OCR service\u2014had to be developed indi\u00advi\u00addu\u00adally. This approach was time-consuming, prone to errors, and made it difficult to reuse existing solutions.<\/p>\n
<\/p>\n
The Model Context Protocol stan\u00addar\u00addizes this access:<\/strong> <\/p>\n <\/p>\n <\/p>\n <\/p>\n OvAItion<\/a>\u2019s AI models and OmnIA<\/a>\u2019s functions \u2013 including OCR, document analysis, and other auto\u00adma\u00adtion tools \u2013 will in future be available directly as tools for an LLM. Pre\u00adde\u00adfined work plans in the form of prompt templates define exactly how, for example, an e\u2011invoice<\/a> is to be processed: which steps are to be taken, in what order, and with which tools.<\/p>\n <\/p>\n Instead of pro\u00adgramming rigid processes, Insiders develops tools and precise gui\u00adde\u00adlines that the LLM combines and executes depending on the situation. This keeps the process flexible without losing precision.<\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n Simpler inte\u00adgra\u00adtion<\/strong> <\/p>\n Greater fle\u00adxi\u00adbi\u00adlity<\/strong> <\/p>\n A step toward true standards<\/strong> <\/p>\n <\/p>\n With projects such as the FHIR Starter, Insiders is already gaining expe\u00adri\u00adence in the deve\u00adlo\u00adp\u00adment of intel\u00adli\u00adgent AI agents. This enables the company to offer pro\u00adto\u00adtypes and pilot solutions at an early stage and secure a head start for its customers in the intro\u00adduc\u00adtion of this new tech\u00adno\u00adlogy.<\/p>\n <\/p>\n <\/p>\n [\/et_pb_text][et_pb_button button_url=\u201c@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9saW5rX3VybF9wYWdlIiwic2V0dGluZ3MiOnsicG9zdF9pZCI6IjgxNjY2In19@\u201c url_new_window=\u201eon\u201c button_text=\u201eMore about AI\u201c button_alignment=\u201eleft\u201c _builder_version=\u201e4.27.4\u201c _dynamic_attributes=\u201ebutton_url\u201c _module_preset=\u201edefault\u201c custom_button=\u201eon\u201c button_text_color=\u201egcid-a1ce49c7-18bb-4621\u20138275-487db4ef4ea2\u201c locked=\u201eoff\u201c global_colors_info=\u201c{%22gcid-e57f936a-e1ef-478a-a91c-6dc2f7bf0652%22:%91%22button_text_color__hover%22%93,%22gcid-a1ce49c7-18bb-4621\u20138275-487db4ef4ea2%22:%91%22button_text_color%22%93}\u201c button_text_color__hover_enabled=\u201eon|hover\u201c button_text_color__hover=\u201e#000000\u201c button_bg_color__hover_enabled=\u201eon|hover\u201c][\/et_pb_button][et_pb_button button_url=\u201ehttps:\/\/insiders.next-kmu.de\/de\/de\/de\/digitalisierung-im-gesundheitswesen-durch-ki-gestuetzte-software\/\u201c url_new_window=\u201eon\u201c button_text=\u201eMore about the FHIR Starter Project\u201c button_alignment=\u201eleft\u201c _builder_version=\u201e4.27.4\u201c _module_preset=\u201edefault\u201c custom_button=\u201eon\u201c button_text_color=\u201egcid-a1ce49c7-18bb-4621\u20138275-487db4ef4ea2\u201c locked=\u201eoff\u201c global_colors_info=\u201c{%22gcid-e57f936a-e1ef-478a-a91c-6dc2f7bf0652%22:%91%22button_text_color__hover%22%93,%22gcid-a1ce49c7-18bb-4621\u20138275-487db4ef4ea2%22:%91%22button_text_color%22%93}\u201c button_text_color__hover_enabled=\u201eon|hover\u201c button_text_color__hover=\u201e#000000\u201c button_bg_color__hover_enabled=\u201eon|hover\u201c][\/et_pb_button][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":" Insiders is inten\u00adsi\u00advely engaged with the question of how arti\u00adfi\u00adcial intel\u00adli\u00adgence will work in the future. Instead of relying on a mono\u00adli\u00adthic \u201call-rounder model,\u201d Insiders is deve\u00adlo\u00adping Agentic AI\u2014a network of spe\u00adcia\u00adlized agents that use the appro\u00adpriate tools depending on the process and make decisions inde\u00adpendently. A central component in this deve\u00adlo\u00adp\u00adment is the Model [\u2026]<\/p>\n","protected":false},"author":28,"featured_media":87088,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","wp_typography_post_enhancements_disabled":false,"_mbp_gutenberg_autopost":false,"footnotes":""},"categories":[677,2],"tags":[],"class_list":["post-88233","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","category-blog-en"],"acf":[],"_links":{"self":[{"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/posts\/88233","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/users\/28"}],"replies":[{"embeddable":true,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/comments?post=88233"}],"version-history":[{"count":0,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/posts\/88233\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/media\/87088"}],"wp:attachment":[{"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/media?parent=88233"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/categories?post=88233"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/insiders.next-kmu.de\/en\/wp-json\/wp\/v2\/tags?post=88233"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
An agent can access different servers via MCP without requiring a separate inte\u00adgra\u00adtion for each con\u00adnec\u00adtion. Each server provides precisely defined tools\u2014for example, an OCR function, an email service, or an SAP connection\u2014as well as resources such as files or documents. The agent dyna\u00admi\u00adcally decides which tools are necessary for the task at hand and combines them into a struc\u00adtured work plan. This allows processes to be imple\u00admented, reused, and flexibly adapted more quickly.<\/p>\nThe vision<\/h3>\n
Relevance for customers<\/h3>\n
With MCP, a one-time imple\u00admen\u00adta\u00adtion is all it takes to make your own tools usable for any number of AI agents\u2014without addi\u00adtional inte\u00adgra\u00adtion efforts for new projects.<\/p>\n
New functions or systems can be connected quickly and easily without having to make costly adjus\u00adt\u00adments to existing processes.<\/p>\n
MCP creates a uniform interface and reduces the pro\u00adli\u00adfe\u00adra\u00adtion of indi\u00advi\u00addual isolated solutions, which brings long-term stability, com\u00adpa\u00adti\u00adbi\u00adlity, and invest\u00adment security.<\/p>\nCurrent status<\/strong><\/h3>\n