{"id":15203,"date":"2025-08-14T10:00:21","date_gmt":"2025-08-14T08:00:21","guid":{"rendered":"https:\/\/www.panter.ch\/?p=15203"},"modified":"2025-12-03T09:34:55","modified_gmt":"2025-12-03T08:34:55","slug":"talk-directly-to-data-with-ai","status":"publish","type":"post","link":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/","title":{"rendered":"How can companies use AI to communicate directly with data?"},"content":{"rendered":"[vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;default&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221;][vc_column_text css=&#8221;&#8221; text_direction=&#8221;default&#8221;]\n<h3>Inhaltsverzeichnis<\/h3>\n[\/vc_column_text]<div class=\"nectar-fancy-ul link_style_underline nectar-link-underline-effect\" data-list-icon=\"fa fa-arrow-down\" data-animation=\"true\" data-animation-delay=\"0\" data-color=\"accent-color\" data-spacing=\"default\" data-alignment=\"left\"> \n<ul>\n<li><a href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#ch1\"><b>KI-Layer und Chat-Bot \u00fcber alle Quellen hinweg<\/b><\/a><\/li>\n<li><strong><a href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#ch2\">Mit Daten sprechen &#8211; Finden statt lange zu suchen<\/a><!-- notionvc: 2f354177-32c3-441f-ac22-cfc34d693a09 --><\/strong><\/li>\n<li><strong><a href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#ch3\">In einer Woche zum Prototyp<\/a><\/strong><\/li>\n<li><strong><a href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#ch4\">Ein Beispiel eines Schweizer KMU<\/a><\/strong><\/li>\n<li><a href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#ch5\"><strong>Eat your own dog food: Pantobot<\/strong><\/a><br \/>\n<!-- notionvc: f9c95263-26ba-4eff-ab55-a1689fc4cb71 --><\/li>\n<\/ul>\n <\/div>[\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;default&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221;][divider line_type=&#8221;Full Width Line&#8221; line_thickness=&#8221;1&#8243; divider_color=&#8221;default&#8221; animate=&#8221;yes&#8221;][\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; top_padding=&#8221;40px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;20px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221; max_width=&#8221;800&#8243;]\n<h3>Ob CRM, Excel, E-Mails oder Fachapplikationen: In vielen Unternehmen schlummern wertvolle Daten, verteilt \u00fcber zig Systeme, die schwer zug\u00e4nglich und oft ungenutzt sind. Ein Kunde von uns sagte mal sehr treffend:<br \/>\n<!-- notionvc: b7e8cefc-ee2a-4adf-ae0c-df03b6c37730 --><!-- notionvc: 310ed2f7-764c-4f29-8a48-5cfb13b44cce --><\/h3>\n[\/vc_column_text][nectar_gradient_text heading_tag=&#8221;h3&#8243; color=&#8221;extra-color-gradient-2&#8243; gradient_direction=&#8221;horizontal&#8221; text=&#8221;&#8220;I always have to ask Ruedi, because this information is all stored in his inbox from the last 10 years.&#8220;&#8221; margin_top=&#8221;48&#8243; margin_bottom=&#8221;48&#8243;][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]<span style=\"font-weight: 400;\">Man sucht zwar im Intranet, findet aber vielfach eine lange Liste von Resultaten, die wenig aussagekr\u00e4ftig sind. Die Folge? Wichtige Entscheidungen werden nach Bauchgef\u00fchl getroffen, statt faktenbasiert.<\/span><\/p>\n<p><!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]Der CEO macht Druck und sagt, das sei doch alles ganz einfach. Man m\u00fcsse nur das CRM an die LinkedIn-Seite koppeln und mit den E-Mails von Ruedi abgleichen, dann w\u00fcsste man alles. Die Welt ist doch vielfach etwas <em>komplexer<\/em>, und wimmelt von unterschiedlichen Berechtigungen, Dateiformaten und dem Mangel an APIs.<\/p>\n<p><!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; top_padding=&#8221;40px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; id=&#8221;ch1&#8243; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;10px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221;]\n<h2>KI-Layer und Chat-Bot \u00fcber alle Quellen hinweg<\/h2>\n[\/vc_column_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]Hier bietet sich nun eine einmalige Chance mit dem Einsatz von KI. Mittels einem KI-Layer k\u00f6nnen verschiedene, sehr <em>heterogene Datenquellen einfach integriert<\/em> werden. \u00c4hnlich wie ein Mensch, schafft man es sowohl semantische wie auch syntaktische Unterschiede unterschiedlicher Systeme gut zu \u00fcberbr\u00fccken. <span style=\"font-weight: 400;\">Die Kunst bei solchen L\u00f6sungen besteht in der Auswahl der passenden KI-Modelle (bspw. das neue Schweizer Modell versus eines bekannten Internationalen). Der KI-Layer abstrahiert diese komplexen Architekturen und stellt ein einfaches API intern zur Verf\u00fcgung.<\/span><\/p>\n<p><!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]<span style=\"font-weight: 400;\">Die zweite St\u00e4rke von KI ist, dass Mitarbeitende mittels Chatbot <em>in nat\u00fcrlicher Sprache<\/em> ihre Anliegen, einfachen Aufgaben und Abfragen formulieren k\u00f6nnen. Was fr\u00fcher spezielle Kenntnisse in Datenbanksprachen wie SQL oder Expertensysteme wie BI-L\u00f6sungen bedingte, erm\u00f6glicht nun jedermann die Interaktion mit spezialisierten Quellsystemen.<\/span><\/p>\n<p><!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; top_padding=&#8221;40px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; id=&#8221;ch2&#8243; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;10px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221;]\n<h2>Mit Daten sprechen, statt lange zu suchen<\/h2>\n<p><!-- notionvc: 6c12655d-e77c-4ca4-847b-8e7987a79330 -->[\/vc_column_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]<span style=\"font-weight: 400;\">It really is a bit like <em>talking directly to data<\/em> with <em>AI<\/em>. Instead of tediously struggling with formats and special queries, you now formulate directly in the chatbot &#8211; instead of <strong>&#8220;SELECT * FROM customers INNER JOIN sales&#8221;<\/strong>, you ask <strong>&#8220;Who bought product X in the last 12 months?&#8221;.<\/strong> ChatGPT shows how it&#8217;s done: instead of receiving countless links like a Google search, you receive a direct answer to a specific question. The big difference is that with Panter&#8217;s solution, <em>internal company data<\/em> can also be used securely, in compliance with Swiss data protection and legally protected. <\/span><!-- notionvc: 456ec290-f57c-4074-b5b4-730b42297b7e --><!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]<span style=\"font-weight: 400;\">Technisch geschieht dies durch eine Wahl einer <em>KI-Architektur<\/em>, welche auf die Vorgaben und Gegebenheiten der jeweiligen Organisation R\u00fccksicht nimmt. Mit der Wahl eines (oder mehreren) KI-Modellen steuert man die Genauigkeit der Antwort (man baut damit den Kontext auf, f\u00fcr den spezifischen KI-Einsatz). Wie in anderen Gebieten ist es stets ein Trade-Off zwischen Genauigkeit und Aufwand. In den meisten F\u00e4llen gen\u00fcgt bereits die Qualit\u00e4t zu erreichen, die man von einem Praktikanten erwarten darf.<\/span><\/p>\n<p><!-- notionvc: 456ec290-f57c-4074-b5b4-730b42297b7e --><br \/>\n<!-- notionvc: 2854c8be-af81-460f-a385-9e20e94f8491 -->[\/nectar_highlighted_text][image_with_animation image_url=&#8221;15469&#8243; image_size=&#8221;full&#8221; max_width=&#8221;100%&#8221; max_width_mobile=&#8221;default&#8221; animation_type=&#8221;entrance&#8221; animation=&#8221;None&#8221; animation_movement_type=&#8221;transform_y&#8221; hover_animation=&#8221;none&#8221; alignment=&#8221;&#8221; border_radius=&#8221;none&#8221; box_shadow=&#8221;none&#8221; image_loading=&#8221;default&#8221;][\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; top_padding=&#8221;40px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; id=&#8221;ch3&#8243; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;10px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221; max_width=&#8221;700&#8243;]\n<h2>In einer Woche zum KI-Prototyp<\/h2>\n<p><!-- notionvc: d8dacc4a-a524-4930-8edc-9a4ef7ab3761 -->[\/vc_column_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#000000&#8243; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]<span style=\"font-weight: 400;\">A proof of concept (PoC) often only takes a week. After that, you know what is possible, can estimate the complexity of all data sources well and have already &#8220;prompted&#8221; (and tested) the first questions. Above all, it becomes clear where the <em>added value<\/em> for the organization lies and how complex the technically and legally correct connection of the most important data sources is. Within <em>two months<\/em>, an <a href=\"https:\/\/www.panter.ch\/en\/minimum-viable-product\/\">MVP<\/a> is ready for productive use and can be used by employees without training. This is how long it usually takes to roll out and train an entire BI solution. Additional data sources can be added on a modular basis. <\/span>[\/nectar_highlighted_text][vc_column_text css=&#8221;&#8221; text_direction=&#8221;default&#8221;]For contractual reasons, we are not allowed to mention all of our customers by name. However, Panter&#8217;s architectures are used by <a href=\"https:\/\/www.panter.ch\/en\/portfolio\/wolfpak-ki-coach\/\">Wolfpak.ai<\/a>, a large company with close ties to the federal government, a Swiss association, an insurance company and in the form of our own internal AI solution &#8220;Pantobot&#8221;.[\/vc_column_text][divider line_type=&#8221;No Line&#8221;][nectar_btn size=&#8221;large&#8221; open_new_tab=&#8221;true&#8221; button_style=&#8221;regular&#8221; button_color_2=&#8221;Accent-Color&#8221; icon_family=&#8221;default_arrow&#8221; text=&#8221;More about the Pantobot&#8221; url=&#8221;https:\/\/www.panter.ch\/en\/stories\/pantobot-our-own-ai-solution\/&#8221; aria_label_text=&#8221;Hier mehr \u00fcber den Pantobot erfahren&#8221; css_animation=&#8221;fadeInUp&#8221;][\/vc_column][\/vc_row][vc_row type=&#8221;full_width_background&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; bg_color=&#8221;#000000&#8243; scene_position=&#8221;center&#8221; top_padding=&#8221;80px&#8221; bottom_padding=&#8221;80px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;light&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; id=&#8221;ch4&#8243; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;10px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221; max_width=&#8221;700&#8243;]\n<h2>Ein Beispiel eines Schweizer KMU<\/h2>\n<p><!-- notionvc: d8dacc4a-a524-4930-8edc-9a4ef7ab3761 -->[\/vc_column_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#FFFFFF&#8221; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]The manager of an SME operating throughout Switzerland approached us with the problem that a lot of data was available, but in systems that could only be accessed by individuals. There was a CMS with event data, a CRM with customer data, an internal drive and personal emails that were often used. Furthermore, it was not possible to adequately track changes in the customers&#8217; VR.[\/nectar_highlighted_text][nectar_highlighted_text color_type=&#8221;regular&#8221; highlight_color=&#8221;#7000FF&#8221; text_color=&#8221;#FFFFFF&#8221; style=&#8221;regular_underline&#8221; highlight_expansion=&#8221;default&#8221; underline_thickness=&#8221;1px&#8221; text_direction=&#8221;default&#8221;]For a PoC, we therefore took CSV exports of the most important systems, a private AI model (data protection) and connected it with Zefix and other public sources. Within days, we had a system that showed the value for the organization and demonstrated its feasibility. With the subsequent MVP, all employees now have access to a chatbot that answers their most important day-to-day questions. The quality of customer service has increased, events can be targeted precisely, changes in relevant customer relationships are visible, etc. And all this without anyone having to manually connect tens of pieces of data.[\/nectar_highlighted_text][\/vc_column][\/vc_row][vc_row type=&#8221;in_container&#8221; full_screen_row_position=&#8221;middle&#8221; column_margin=&#8221;default&#8221; column_direction=&#8221;default&#8221; column_direction_tablet=&#8221;default&#8221; column_direction_phone=&#8221;default&#8221; scene_position=&#8221;center&#8221; top_padding=&#8221;40px&#8221; top_padding_phone=&#8221;12vw&#8221; text_color=&#8221;dark&#8221; text_align=&#8221;left&#8221; row_border_radius=&#8221;none&#8221; row_border_radius_applies=&#8221;bg&#8221; overflow=&#8221;visible&#8221; id=&#8221;ch5&#8243; overlay_strength=&#8221;0.3&#8243; gradient_direction=&#8221;left_to_right&#8221; shape_divider_position=&#8221;bottom&#8221; bg_image_animation=&#8221;none&#8221; gradient_type=&#8221;default&#8221; shape_type=&#8221;&#8221;][vc_column column_padding=&#8221;no-extra-padding&#8221; column_padding_tablet=&#8221;inherit&#8221; column_padding_phone=&#8221;inherit&#8221; column_padding_position=&#8221;all&#8221; column_element_direction_desktop=&#8221;default&#8221; column_element_spacing=&#8221;10px&#8221; desktop_text_alignment=&#8221;default&#8221; tablet_text_alignment=&#8221;default&#8221; phone_text_alignment=&#8221;default&#8221; background_color_opacity=&#8221;1&#8243; background_hover_color_opacity=&#8221;1&#8243; column_backdrop_filter=&#8221;none&#8221; column_shadow=&#8221;none&#8221; column_border_radius=&#8221;none&#8221; column_link_target=&#8221;_self&#8221; column_position=&#8221;default&#8221; gradient_direction=&#8221;left_to_right&#8221; overlay_strength=&#8221;0.3&#8243; width=&#8221;1\/1&#8243; tablet_width_inherit=&#8221;default&#8221; animation_type=&#8221;default&#8221; bg_image_animation=&#8221;none&#8221; border_type=&#8221;simple&#8221; column_border_width=&#8221;none&#8221; column_border_style=&#8221;solid&#8221; column_padding_type=&#8221;default&#8221; gradient_type=&#8221;default&#8221;][vc_column_text css_animation=&#8221;fadeInUp&#8221; css=&#8221;&#8221; text_direction=&#8221;default&#8221; max_width=&#8221;700&#8243;]\n<h2>Eat your own dog food: Pantobot.<\/h2>\n<p><!-- notionvc: d8dacc4a-a524-4930-8edc-9a4ef7ab3761 -->[\/vc_column_text][nectar_highlighted_text color_type=&#8221;regular&#8221; style=&#8221;full_text&#8221; highlight_expansion=&#8221;default&#8221; text_direction=&#8221;default&#8221;]In Pantobot, we have implemented precisely this architecture ourselves and use both internal and external data sources. All employees have access to it and can use it in their daily work. Especially in project management, we see great simplifications in daily work, e.g. details of time recording, project reporting and requirements engineering have become much easier. The feedback from employees can be roughly summarized as follows:[\/nectar_highlighted_text][divider line_type=&#8221;No Line&#8221;]<div class=\"nectar-fancy-ul\" data-list-icon=\"icon-salient-check\" data-animation=\"true\" data-animation-delay=\"0\" data-color=\"accent-color\" data-spacing=\"5px\" data-alignment=\"left\"> \n<ul>\n<li><b>Schnellere Entscheidungen<\/b><span style=\"font-weight: 400;\">, weil die Antwort direkt kommt und in \u00abnormalem\u00bb Deutsch.<\/span><\/li>\n<li><b>Bessere Datennutzung<\/b><span style=\"font-weight: 400;\">, weil bis dato separate Silos nun verbunden sind.<\/span><\/li>\n<li><b>Entlastung von Experten<\/b><span style=\"font-weight: 400;\">, weil Wissen direkt geteilt und verf\u00fcgbar ist.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/li>\n<li><b>Neue Perspektiven<\/b><span style=\"font-weight: 400;\">, weil externe Quellen (z.B. Standortdaten, <a href=\"https:\/\/www.zefix.ch\/de\/search\/entity\/welcome\">Zefix<\/a>) zus\u00e4tzlich verkn\u00fcpft werden.<\/span><\/li>\n<li><b>Schweiz-konform, <\/b><span style=\"font-weight: 400;\">erf\u00fcllt somit datenschutzrechtliche Vorgaben und Compliance gem\u00e4ss Schweizer Vorgaben.<\/span><\/li>\n<\/ul>\n <\/div>[vc_column_text css=&#8221;&#8221; text_direction=&#8221;default&#8221;]Wir haben unsere Datensilos erfolgreich verbunden. W\u00e4ren Sie neugierig zu erfahren, welches ungenutzte Potenzial sich freisetzen liesse, wenn auch Sie Ihre internen und externen Datenquellen intelligent miteinander verkn\u00fcpfen w\u00fcrden? Kontaktieren Sie uns jetzt \u2013 in nur einer Woche zeigen wir Ihnen mithilfe eines Prototyps, welche verborgenen Sch\u00e4tze in Ihren Daten schlummern.<br \/>\n<!-- notionvc: 6562536d-bf1f-4a74-85a6-2aa2c36a87f6 -->[\/vc_column_text][divider line_type=&#8221;No Line&#8221;][nectar_btn size=&#8221;large&#8221; open_new_tab=&#8221;true&#8221; button_style=&#8221;regular&#8221; button_color_2=&#8221;Accent-Color&#8221; icon_family=&#8221;default_arrow&#8221; text=&#8221;Contact us&#8221; url=&#8221;https:\/\/www.panter.ch\/en\/contact\/&#8221; css_animation=&#8221;fadeInUp&#8221;][\/vc_column][\/vc_row]\n","protected":false},"excerpt":{"rendered":"<p>How Swiss companies are finally using artificial intelligence (AI) to bring clarity to their data.<\/p>\n","protected":false},"author":3,"featured_media":15296,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"inline_featured_image":false,"footnotes":""},"categories":[276,358,274],"tags":[],"class_list":["post-15203","post","type-post","status-publish","format-standard","has-post-thumbnail","category-ai-data-en","category-ai-applications","category-blog-en"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v27.7 (Yoast SEO v27.7) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>Using AI to talk directly to data and make informed decisions<\/title>\n<meta name=\"description\" content=\"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How can companies use AI to communicate directly with data?\" \/>\n<meta property=\"og:description\" content=\"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"Panter AG\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/panterch\" \/>\n<meta property=\"article:published_time\" content=\"2025-08-14T08:00:21+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-03T08:34:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1440\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Roberto\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@panterch\" \/>\n<meta name=\"twitter:site\" content=\"@panterch\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Roberto\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/\"},\"author\":{\"name\":\"Roberto\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#\\\/schema\\\/person\\\/17955a8092d4a5671347f2f158635479\"},\"headline\":\"How can companies use AI to communicate directly with data?\",\"datePublished\":\"2025-08-14T08:00:21+00:00\",\"dateModified\":\"2025-12-03T08:34:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/\"},\"wordCount\":2954,\"publisher\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg\",\"articleSection\":[\"AI &amp; Data\",\"AI Applications\",\"Blog\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/\",\"url\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/\",\"name\":\"Using AI to talk directly to data and make informed decisions\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg\",\"datePublished\":\"2025-08-14T08:00:21+00:00\",\"dateModified\":\"2025-12-03T08:34:55+00:00\",\"description\":\"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg\",\"width\":2560,\"height\":1440,\"caption\":\"Ein reflektierendes, kapself\u00f6rmiges Objekt zeigt den Text How do large language models work? vor einem violetten, futuristischen Hintergrund mit geometrischen Mustern, der andeutet, wie Mit KI direkt mit Daten sprechen m\u00f6glich wird.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/stories\\\/talk-directly-to-data-with-ai\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/salient-architect-landing\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How can companies use AI to communicate directly with data?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/\",\"name\":\"Panter AG\",\"description\":\"Smarter, better, human.\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#organization\",\"name\":\"Panter AG\",\"alternateName\":\"Panter\",\"url\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/Panter_Favicon_696x696.jpg\",\"contentUrl\":\"https:\\\/\\\/www.panter.ch\\\/wp-content\\\/uploads\\\/Panter_Favicon_696x696.jpg\",\"width\":696,\"height\":696,\"caption\":\"Panter AG\"},\"image\":{\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/panterch\",\"https:\\\/\\\/x.com\\\/panterch\",\"https:\\\/\\\/ch.linkedin.com\\\/company\\\/panter-ch\",\"https:\\\/\\\/www.instagram.com\\\/panter.ch\\\/\",\"https:\\\/\\\/github.com\\\/panter\"],\"description\":\"Wir von Panter sind Macher und Techies mit interdisziplin\u00e4rem Know-how \u2013 von Softwareentwicklung \u00fcber Design bis zu AI-Expertise. Mit innovativen, nutzerzentrierten L\u00f6sungen, modernster Technologie und einem starken Netzwerk entwickeln wir Services, die Ihre Nutzer begeistern und Ihr Unternehmen voranbringen. Als Schweizer Software- und Beratungsunternehmen stehen wir f\u00fcr Qualit\u00e4t, Innovationskraft und partnerschaftliche Zusammenarbeit \u2013 mit Herz und Verstand.\",\"email\":\"hello@panter.ch\",\"telephone\":\"+41 44 500 29 04\",\"legalName\":\"Panter AG\",\"foundingDate\":\"2005-01-01\",\"vatID\":\"CHE-262.202.358\",\"numberOfEmployees\":{\"@type\":\"QuantitativeValue\",\"minValue\":\"11\",\"maxValue\":\"50\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.panter.ch\\\/en\\\/#\\\/schema\\\/person\\\/17955a8092d4a5671347f2f158635479\",\"name\":\"Roberto\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g\",\"caption\":\"Roberto\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Using AI to talk directly to data and make informed decisions","description":"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/","og_locale":"en_US","og_type":"article","og_title":"How can companies use AI to communicate directly with data?","og_description":"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.","og_url":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/","og_site_name":"Panter AG","article_publisher":"https:\/\/www.facebook.com\/panterch","article_published_time":"2025-08-14T08:00:21+00:00","article_modified_time":"2025-12-03T08:34:55+00:00","og_image":[{"width":2560,"height":1440,"url":"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg","type":"image\/jpeg"}],"author":"Roberto","twitter_card":"summary_large_image","twitter_creator":"@panterch","twitter_site":"@panterch","twitter_misc":{"Written by":"Roberto","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#article","isPartOf":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/"},"author":{"name":"Roberto","@id":"https:\/\/www.panter.ch\/en\/#\/schema\/person\/17955a8092d4a5671347f2f158635479"},"headline":"How can companies use AI to communicate directly with data?","datePublished":"2025-08-14T08:00:21+00:00","dateModified":"2025-12-03T08:34:55+00:00","mainEntityOfPage":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/"},"wordCount":2954,"publisher":{"@id":"https:\/\/www.panter.ch\/en\/#organization"},"image":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg","articleSection":["AI &amp; Data","AI Applications","Blog"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/","url":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/","name":"Using AI to talk directly to data and make informed decisions","isPartOf":{"@id":"https:\/\/www.panter.ch\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#primaryimage"},"image":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg","datePublished":"2025-08-14T08:00:21+00:00","dateModified":"2025-12-03T08:34:55+00:00","description":"No more searching the intranet. We explain how you can use AI to talk directly to your data and get answers immediately.","breadcrumb":{"@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#primaryimage","url":"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg","contentUrl":"https:\/\/www.panter.ch\/wp-content\/uploads\/google-deepmind-jJMqaZU4EnU-unsplash-scaled.jpg","width":2560,"height":1440,"caption":"Ein reflektierendes, kapself\u00f6rmiges Objekt zeigt den Text How do large language models work? vor einem violetten, futuristischen Hintergrund mit geometrischen Mustern, der andeutet, wie Mit KI direkt mit Daten sprechen m\u00f6glich wird."},{"@type":"BreadcrumbList","@id":"https:\/\/www.panter.ch\/en\/stories\/talk-directly-to-data-with-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.panter.ch\/en\/salient-architect-landing\/"},{"@type":"ListItem","position":2,"name":"How can companies use AI to communicate directly with data?"}]},{"@type":"WebSite","@id":"https:\/\/www.panter.ch\/en\/#website","url":"https:\/\/www.panter.ch\/en\/","name":"Panter AG","description":"Smarter, better, human.","publisher":{"@id":"https:\/\/www.panter.ch\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.panter.ch\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.panter.ch\/en\/#organization","name":"Panter AG","alternateName":"Panter","url":"https:\/\/www.panter.ch\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.panter.ch\/en\/#\/schema\/logo\/image\/","url":"https:\/\/www.panter.ch\/wp-content\/uploads\/Panter_Favicon_696x696.jpg","contentUrl":"https:\/\/www.panter.ch\/wp-content\/uploads\/Panter_Favicon_696x696.jpg","width":696,"height":696,"caption":"Panter AG"},"image":{"@id":"https:\/\/www.panter.ch\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/panterch","https:\/\/x.com\/panterch","https:\/\/ch.linkedin.com\/company\/panter-ch","https:\/\/www.instagram.com\/panter.ch\/","https:\/\/github.com\/panter"],"description":"Wir von Panter sind Macher und Techies mit interdisziplin\u00e4rem Know-how \u2013 von Softwareentwicklung \u00fcber Design bis zu AI-Expertise. Mit innovativen, nutzerzentrierten L\u00f6sungen, modernster Technologie und einem starken Netzwerk entwickeln wir Services, die Ihre Nutzer begeistern und Ihr Unternehmen voranbringen. Als Schweizer Software- und Beratungsunternehmen stehen wir f\u00fcr Qualit\u00e4t, Innovationskraft und partnerschaftliche Zusammenarbeit \u2013 mit Herz und Verstand.","email":"hello@panter.ch","telephone":"+41 44 500 29 04","legalName":"Panter AG","foundingDate":"2005-01-01","vatID":"CHE-262.202.358","numberOfEmployees":{"@type":"QuantitativeValue","minValue":"11","maxValue":"50"}},{"@type":"Person","@id":"https:\/\/www.panter.ch\/en\/#\/schema\/person\/17955a8092d4a5671347f2f158635479","name":"Roberto","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/63049a62ffa6445b337ce3fa0e7ad5dbf289f7541d5f9e0f10d871cc3b4241a8?s=96&d=mm&r=g","caption":"Roberto"}}]}},"_links":{"self":[{"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/posts\/15203","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/comments?post=15203"}],"version-history":[{"count":34,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/posts\/15203\/revisions"}],"predecessor-version":[{"id":16657,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/posts\/15203\/revisions\/16657"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/media\/15296"}],"wp:attachment":[{"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/media?parent=15203"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/categories?post=15203"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.panter.ch\/en\/wp-json\/wp\/v2\/tags?post=15203"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}