{"id":39498,"date":"2026-05-14T22:20:11","date_gmt":"2026-05-14T20:20:11","guid":{"rendered":"https:\/\/www.logicline.de\/ai-in-service-own-knowledge-base"},"modified":"2026-08-16T13:47:51","modified_gmt":"2026-08-16T11:47:51","slug":"ai-in-service-own-knowledge-base","status":"publish","type":"post","link":"https:\/\/www.logicline.de\/en\/ai-in-service-own-knowledge-base","title":{"rendered":"When Agentforce Hallucinates: Why AI in Customer Service Needs Its Own Knowledge Base"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"39498\" class=\"elementor elementor-39498 elementor-39489\" data-elementor-post-type=\"post\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7c03afc0 e-flex e-con-boxed e-con e-parent\" data-id=\"7c03afc0\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-61419d4e elementor-widget elementor-widget-text-editor\" data-id=\"61419d4e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<strong>Incorrect AI responses in the service area jeopardize decisions.<\/strong> When it comes to warranty claims or maintenance requests, generic AI models often provide inaccurate information: nonexistent fault codes, incorrect contract details, or inappropriate maintenance steps. The reason: Such models are based on probabilities, not on reliable facts. A standalone knowledge base like <strong>Service Decision Intelligence (SDI)<\/strong> addresses this issue by consolidating data from IoT, ERP, and CRM systems and making AI decisions transparent.\n\n<strong>Key points:<\/strong>\n<ul>\n \t<li><strong>Problem:<\/strong> Generic AI models tend to hallucinate because they lack specific service data.<\/li>\n \t<li><strong>Solution:<\/strong> SDI provides a central intelligence layer with source citations and confidence scores.<\/li>\n \t<li><strong>Result:<\/strong> Faster, more precise decisions that are auditable and AI Act-compliant.<\/li>\n<\/ul>\nIn practice, it has become clear that SDI not only streamlines day-to-day operations in customer service but also lays the groundwork for automation.\n<h2>A typical scenario: Claims triage with and without SDI<\/h2>\n<h3>Here&#8217;s How Claims Triage Works Today<\/h3>\nA complaint is reported. At first glance, it appears to be a warranty claim\u2014but is that really the case? To clarify this, the employee in charge accesses various sources: IoT data, Salesforce, ERP systems, and PDF archives. Each of these sources provides only one piece of the puzzle, and there is no seamless connection between them.\n\nThe decision as to whether a case is classified under warranty, goodwill or as chargeable depends on whether an experienced employee compiles all the information correctly. Phone calls, email correspondence and the manual comparison of Excel lists characterize the daily work routine in many service organizations &#8211; even at manufacturers who have long since digitized their data.\n\nWhen experienced employees leave the company, valuable knowledge is often lost. Using a generic LLM (Large Language Model) as a substitute carries risks: Such models may generate incorrect fault codes, misjudge contract terms, or suggest maintenance steps intended for other machines. In contrast, SDI offers reliable and fully integrated data preparation.\n<h3>How SDI Is Changing Claims Triage<\/h3>\nWith SDI, a service case is automatically populated with relevant information right from the start: IoT telemetry data, contract details from Salesforce, material batches and warranty periods from the ERP system, as well as relevant sections from the technical documentation\u2014all without having to manually switch between systems.\n\nSDI provides a pre-classified recommendation\u2014such as \u201cwarranty,\u201d \u201cgoodwill,\u201d or \u201csubject to a fee\u201d\u2014supplemented by a confidence score and notes on potential data gaps. If, for example, proof of maintenance is missing, this is clearly indicated rather than presenting assumptions as facts. Each recommendation includes a <strong>source citation<\/strong> that makes it clear on what data the decision is based. This ensures that the solution is auditable from the outset and complies with the requirements of the <a href=\"https:\/\/www.europarl.europa.eu\/topics\/en\/article\/20230601STO93804\/eu-ai-act-first-regulation-on-artificial-intelligence\" target=\"_blank\" rel=\"noopener\">AI Act<\/a>.\n\nThe key difference is that people make the final decision &#8211; but on the basis of sound information, not in uncertainty.\n\n<img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone wp-image-42559 size-large\" src=\"https:\/\/www.logicline.de\/wp-content\/uploads\/2026\/08\/claims-triage-sdi-vs-llm-en.svg\" alt=\"Claims Triage: Without SDI vs. With SDI\" width=\"800\" height=\"449\" \/>\n\nAn office worker asks a simple question in natural language: <em>\u201cWhy has Machine 41788 been breaking down more frequently over the past six weeks?\u201d<\/em>\n\nWithout SDI, this means that tickets, IoT dashboards, and service documentation must be searched manually\u2014with results that depend heavily on who is available at the time.\n\nWith SDI, on the other hand, the intelligence layer simultaneously analyzes IoT time series, open and closed tickets, and technical documentation. The result is a precise answer that includes a source citation, a confidence score, and clearly identified data gaps. This is not a \u201cblack box\u201d response, but rather a <strong>citable diagnosis<\/strong> that transparently shows which sensor data was decisive, which ticket contains the relevant information, and which section of the operating instructions is affected. The inside sales staff can process this information directly.\n\nIt\u2019s important to note that SDI acts as an intelligence layer between the data and the AI agent\u2014it is not the front end itself, but rather the foundation for informed decisions.\n<div class=\"callout\">\n<p style=\"margin: 0;\"><strong>In 30 minutes, we&#8217;ll determine where your service data isn&#8217;t yet integrated\u2014and where SDI would come into play.<\/strong><\/p>\nUsing a specific service case from your machine fleet, we\u2019ll show you which sources are currently missing and what a citable diagnosis\u2014complete with a confidence score and source citations\u2014would look like. This isn\u2019t a generic AI pitch\u2014it\u2019s a look at your specific data situation.\n\u2192 <a href=\"https:\/\/www.logicline.de\/en\/contact\"><strong>Schedule an introductory call<\/strong><\/a>\n\n<\/div>\n<h2>8 Reasons Why SDI Protects AI Agents from Hallucinations<\/h2>\nSDI offers eight clear advantages for preventing hallucinations by generic AI agents while enabling reliable, transparent decisions.\n<h3>Confidence scores and named data gaps<\/h3>\nWhile generic AI models often provide answers with apparent certainty, even when the data set is insufficient, SDI takes a different approach. Each recommendation includes a <strong>confidence score<\/strong> that transparently indicates the reliability of the statement. In addition, SDI actively tests hypotheses for counterevidence. For example, if maintenance records are missing or sensor readings are incomplete, this is explicitly noted. This ensures that users can clearly understand the basis for the recommendation and identify where uncertainties exist.\n\nReliable AI must be able to acknowledge uncertainty\u2014presenting assumptions as facts is more dangerous than honestly acknowledging data gaps. This is exactly the approach SDI takes.\n<h3>Persistent audit trail and AI Act compliance from day 1<\/h3>\nWith SDI, every response is documented by an <strong>immutable audit trail<\/strong>. This trail shows exactly which sensor data, tickets, or ERP entries form the basis for a recommendation. Since the audit trail cannot be edited retroactively, it meets the transparency and traceability requirements of the EU AI Act from the very beginning. For heads of service, this means that every decision is fully auditable.\n<h3>Cross-asset reasoning across fleets and locations<\/h3>\nA single machine log is often not enough to get a comprehensive picture. SDI analyzes patterns <strong>across the entire installed base<\/strong> \u2014regardless of locations, machine types, or operating environments. For example, if ten machines of a certain type exhibit similar anomalies within a specific time frame, SDI identifies these correlations. This enables fleet-wide analysis that goes far beyond individual case diagnostics and provides companies with centralized control over their data infrastructure.\n<h3>Data sovereignty in Your Own Cloud<\/h3>\nSDI runs directly on the customer\u2019s infrastructure\u2014either on Azure, AWS, or Heroku\u2014 <strong>not in a shared environment<\/strong>. As a result, service data, machine data, and contract histories remain within the customer\u2019s own cloud and are not used in external LLM training. This solution not only meets industry-specific data protection requirements but also allows for flexible integration into existing systems.\n<h3>LLM- and agent-agnostic via MCP<\/h3>\nSDI is independent of any specific AI front end. Using the <strong>Model Context Protocol (MCP)<\/strong> \u2014an open standard for connecting context sources to AI models\u2014the intelligence layer can be connected to Agentforce, Claude, Copilot, or other agents. Even if the front end is changed, the entire domain logic\u2014including the knowledge base, confidence logic, and audit trails\u2014remains intact.\n<h3>Headless 360 and Bidirectional Availability<\/h3>\nThe SDI functions are available both as <strong>a REST action for Agentforce<\/strong> and as <strong>an MCP tool for other AI front ends<\/strong>. Without proprietary formats or vendor lock-in, the same diagnostic logic can be used in parallel across different systems. The open architecture enables flexible and future-proof integration.\n<h3>10-12 weeks to productivity instead of 6-12 months<\/h3>\nUnlike in-house developments, which often take 6\u201312 months, SDI\u2014with its six prebuilt skills\u2014is ready for use in just 10\u201312 weeks. This not only saves development time but also eliminates the effort required to build an in-house RAG infrastructure from scratch.\n<h3>An Overview of the Six SDI Skills<\/h3>\nThe six skills form a comprehensive intelligence layer for the machinery and equipment service:\n<div class=\"tbl\">\n<table id=\"T0\"><colgroup> <col \/> <col \/><\/colgroup>\n<thead>\n<tr>\n<th id=\"T0-A0\" class=\"A0 tooltip\">SDI Skill<\/th>\n<th id=\"T0-B0\" class=\"B0 tooltip\">Function<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td id=\"T0-A1\" class=\"A1 tooltip\"><strong>Telemetry analysis<\/strong><\/td>\n<td id=\"T0-B1\" class=\"B1 tooltip\">Analysis of IoT time series<\/td>\n<\/tr>\n<tr>\n<td id=\"T0-A2\" class=\"A2 tooltip\"><strong>CRM Context via GRAX<\/strong><\/td>\n<td id=\"T0-B2\" class=\"B2 tooltip\">Salesforce history without API limits\u2014service cases, contracts, and complaints related to a machine spanning several years<\/td>\n<\/tr>\n<tr>\n<td id=\"T0-A3\" class=\"A3 tooltip\"><strong>ERP data<\/strong><\/td>\n<td id=\"T0-B3\" class=\"B3 tooltip\">Material, batches, orders and warranty periods from the ERP<\/td>\n<\/tr>\n<tr>\n<td id=\"T0-A4\" class=\"A4 tooltip\"><strong>Technical Knowledge via RAG<\/strong><\/td>\n<td id=\"T0-B4\" class=\"B4 tooltip\">Technical documentation becomes searchable via Retrieval Augmented Generation; logicline helped develop the Salesforce integration for Empolis Service Express<\/td>\n<\/tr>\n<tr>\n<td id=\"T0-A5\" class=\"A5 tooltip\"><strong>Diagnostic Synthesis<\/strong><\/td>\n<td id=\"T0-B5\" class=\"B5 tooltip\">Claims, RMA, and Warranty Triage with Confidence Score, Cross-Asset Analysis, and Audit Trail<\/td>\n<\/tr>\n<tr>\n<td id=\"T0-A6\" class=\"A6 tooltip\"><strong>Proactive insights<\/strong><\/td>\n<td id=\"T0-B6\" class=\"B6 tooltip\">Pattern recognition across the entire fleet for early recommendations for action<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\nFor more details on the individual skills, please visit the <a href=\"https:\/\/www.logicline.de\/en\/services\/service-decision-intelligence\">SDI Services page<\/a>.\n<h2>SDI as the intelligence layer behind AI front ends<\/h2>\n<h3>SDI vs. Generic AI Front Ends: The Roles of the Individual Layers<\/h3>\nSDI lays the foundation for reliable front ends by seamlessly integrating data from various sources, such as IoT, Salesforce, ERP, and technical documentation. Front-ends like Agentforce or Copilot can produce erroneous results without a domain-specific knowledge base\u2014not because of poor models, but because of a lack of structured data. A separate article explains why a <a href=\"https:\/\/www.logicline.de\/en\/ki-assistant-service-machine-context\">generic AI assistant cannot answer the most important service question<\/a> \u2014because it lacks machine context. This is where SDI comes in: It acts as an intelligence layer that bridges this gap and processes data transparently.\n\nA knowledge base provides the agent with external data\u2014product details, service histories, fault codes\u2014that it accesses for every response. Without this source, the LLM remains reliant on the statistical probability of its own training data. SDI\u2019s strength lies in providing a robust knowledge base with source citations, confidence scores, and a permanent audit trail. While the front end remains flexibly interchangeable, SDI ensures stable, domain-specific logic.\n\nThis clear separation between the knowledge base and the front end facilitates integration into existing systems and ensures that the results remain reliable.\n<h3>Native Salesforce data model instead of external overlays<\/h3>\nSDI operates directly on the native Salesforce data model and does not require any additional overlays. It leverages existing structures such as asset hierarchies, service histories, and the installed base. Changes made in the CRM are reflected in the knowledge base in real time, without the need for additional synchronization logic.\n\nOne example of this is the <strong>Digital Machine File<\/strong>, which integrates configuration histories, the installed base, and IoT data directly into Salesforce. This approach eliminates the need for separate data transfers, and the information remains up to date at all times.\n\nWith this native approach, SDI offers not only real-time integration but also a high level of reliability, especially for industry-specific requirements.\n<h3>Industry-specific precision and control over the infrastructure<\/h3>\nGeneric AI models are designed for general use cases and often lack specific knowledge relevant to special-purpose machine manufacturing\u2014such as details on fault codes, component generations, or maintenance cycles. SDI bridges this gap by providing precisely this information in a structured format and making it accessible to AI agents.\n\nAnother key advantage: SDI runs on the customer\u2019s infrastructure\u2014such as Azure or AWS\u2014rather than in a shared environment. This ensures data sovereignty and meets the requirements of the AI Act. Service data remains protected and is not incorporated into external training models. Every response is based on a traceable and auditable dataset, ensuring maximum transparency.\n\nThis combination of domain-specific knowledge and strict infrastructure control is what fundamentally sets SDI apart from generic solutions.\n<h2>SDI in logicline&#8217;s Service Architecture<\/h2>\n<h3>Basis: The 4-step model<\/h3>\nSDI is not being introduced as a standalone solution, but rather builds on the previous stages of the 4-step model:\n<ul>\n \t<li><strong>Step 1 \u2014 Digitize:<\/strong> The <a href=\"https:\/\/www.logicline.de\/en\/services\/digital-machine-file\">Digital Machine File<\/a> in Salesforce creates a structured database.<\/li>\n \t<li><strong>Phase 2 \u2014 Connect:<\/strong> The <a href=\"https:\/\/www.logicline.de\/en\/services\/installed-base-assessment\">Installed Base Assessment<\/a> consolidates and cleanses distributed master data; the IoT platform, ERP, and knowledge sources are connected to Salesforce.<\/li>\n \t<li><strong>Stage 3 \u2014 Decide:<\/strong> SDI uses the connected data as a knowledge base and provides AI agents with answers that include source citations, confidence scores, and a persistent audit trail.<\/li>\n \t<li><strong>Level 4 \u2014 Automate:<\/strong> Building on SDI, defined service tasks can be performed autonomously \u2014 the transition to Service as Software.<\/li>\n<\/ul>\nWithout a complete and accurate machine profile and a consolidated installed base, any AI integration remains unreliable. This groundwork is crucial for efficiently integrating specialized partner solutions.\n<h3>Integration of Partner Solutions: GRAX and Empolis Service Express<\/h3>\nTwo key partner solutions contribute significantly to SDI&#8217;s knowledge base.\n<ul>\n \t<li><strong>GRAX:<\/strong> This solution provides comprehensive access to Salesforce data histories\u2014including service cases, contracts, and complaints\u2014spanning multiple years\u2014without being limited by API quotas. This gives the AI agent a complete overview of an object\u2019s lifecycle, rather than just access to current data.<\/li>\n \t<li><strong>Empolis Service Express:<\/strong> This is where technical documentation expertise comes into play. Using Retrieval Augmented Generation, users can perform targeted searches for manuals, fault codes, and maintenance instructions. logicline helped develop the Salesforce integration for Empolis Service Express, which combines technical knowledge and CRM data into a unified search logic. Our article, <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/knowledge-management-in-the-mechanical-engineering-service-sector\" target=\"_blank\" rel=\"noopener noreferrer\">\u201cKnowledge Management in Service<\/a>,\u201d takes an in-depth look at how this knowledge base is methodically built\u2014from data entry in the ticket system to linking it to the machine file.<\/li>\n<\/ul>\n<h3>The Path to Automation: Level 4 and Service as Software<\/h3>\nThe implementation of SDI in Stage 3\u2014Decide\u2014lays the foundation for automation in Stage 4. Decisions that are currently reviewed and made by humans can be automated in the future. For example: If a decision\u2019s confidence score exceeds a specified threshold, the same logic that currently notifies an employee can automatically trigger a service order in the future. SDI makes decisions not only machine-readable but also repeatable. This paves the way for a seamless transition to automation.\n<h2>Conclusion: What SDI Means for Your Service Business<\/h2>\n<h3>The most important findings<\/h3>\nWithout a domain-specific knowledge base, generic AI agents quickly reach their limits: The answers they provide are often unreliable and unverifiable\u2014in claims or warranty triage, this leads to incorrect classifications and associated costs. This is exactly where SDI comes in and closes this gap.\n\nWith SDI, your service data is converted into a citable knowledge base. This includes source citations, confidence scores, and explicitly highlights existing data gaps. This ensures that decisions are based on well-founded and traceable information. SDI is a central component of the third stage\u2014 <strong>Decide<\/strong> \u2014and paves the way for the gradual automation of your service processes.\n\nAnother advantage: SDI ensures your data sovereignty by using its own cloud infrastructure (Azure or AWS) and, thanks to the MCP architecture, remains independent of specific LLMs. The solution is directly AI-Act compliant and offers flexibility in system integration. The front end can be replaced, while the intelligence layer remains entirely under your control.\n\nThe first step isn\u2019t the <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/ai-projects-service-data-readiness\" target=\"_blank\" rel=\"noopener noreferrer\">next AI pilot project<\/a>, but an honest <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/service-data-readiness-check\" target=\"_blank\" rel=\"noopener noreferrer\">assessment of your current data landscape<\/a>. The <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/services\/installed-base-assessment\" target=\"_blank\" rel=\"noopener noreferrer\">Installed Base Assessment<\/a> shows which service data is currently available, which of the six SDI skills offer the greatest leverage, and in what order SDI will go live in your service architecture\u2014typically within 10 to 12 weeks. If you already have a structured foundation and would like to evaluate directly how SDI applies to specific service cases, schedule an <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/contact\" target=\"_blank\" rel=\"noopener noreferrer\">introductory call<\/a>. Details on the architecture, the six skills, and the MCP integration with Agentforce, Claude, or Copilot can be found on the <a class=\"text-[var(--accent)] hover:underline underline-offset-[1px] outline-none hide-focus-ring ring-focus rounded-r2\" href=\"https:\/\/www.logicline.de\/en\/services\/service-decision-intelligence\" target=\"_blank\" rel=\"noopener noreferrer\">Service Decision Intelligence services page<\/a>.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<section data-dce-background-color=\"#00000000\" class=\"elementor-element elementor-element-c254285 e-flex e-con-boxed e-con e-parent\" data-id=\"c254285\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div data-dce-background-color=\"#FFFFFF\" class=\"elementor-element elementor-element-55aff5e e-flex e-con-boxed e-con e-child\" data-id=\"55aff5e\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-48de356 e-con-full e-flex e-con e-child\" data-id=\"48de356\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t<div class=\"elementor-element elementor-element-4b7d6a6 e-flex e-con-boxed e-con e-child\" data-id=\"4b7d6a6\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0fa94fe elementor-widget elementor-widget-heading\" data-id=\"0fa94fe\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">FAQs<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ed3a7f2 elementor-widget elementor-widget-n-accordion\" data-id=\"ed3a7f2\" data-element_type=\"widget\" data-e-type=\"widget\" data-settings=\"{&quot;default_state&quot;:&quot;expanded&quot;,&quot;max_items_expended&quot;:&quot;one&quot;,&quot;n_accordion_animation_duration&quot;:{&quot;unit&quot;:&quot;ms&quot;,&quot;size&quot;:400,&quot;sizes&quot;:[]}}\" data-widget_type=\"nested-accordion.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<div class=\"e-n-accordion\" aria-label=\"Accordion. Open links with Enter or Space, close with Escape, and navigate with Arrow Keys\">\n\t\t\t\t\t\t<details id=\"e-n-accordion-item-2480\" class=\"e-n-accordion-item\" open>\n\t\t\t\t<summary class=\"e-n-accordion-item-title\" data-accordion-index=\"1\" tabindex=\"0\" aria-expanded=\"true\" aria-controls=\"e-n-accordion-item-2480\" >\n\t\t\t\t\t<span class='e-n-accordion-item-title-header'><h4 class=\"e-n-accordion-item-title-text\"> What data does SDI need to ensure that AI doesn't \"hallucinate\" in the service? <\/h4><\/span>\n\t\t\t\t\t\t\t<span class='e-n-accordion-item-title-icon'>\n\t\t\t<span class='e-opened' ><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-minus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t\t<span class='e-closed'><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-plus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H272V64c0-17.67-14.33-32-32-32h-32c-17.67 0-32 14.33-32 32v144H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h144v144c0 17.67 14.33 32 32 32h32c17.67 0 32-14.33 32-32V304h144c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t<\/span>\n\n\t\t\t\t\t\t<\/summary>\n\t\t\t\t<div role=\"region\" aria-labelledby=\"e-n-accordion-item-2480\" class=\"elementor-element elementor-element-8046bac e-flex e-con-boxed e-con e-child\" data-id=\"8046bac\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-e3a4f16 elementor-widget elementor-widget-text-editor\" data-id=\"e3a4f16\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><p>For AI to make precise and reliable decisions in customer service, a targeted knowledge base is essential. <em>Service Decision Intelligence (SDI)<\/em> combines machine data, CRM history, ERP data, and technical expertise into a structured foundation. Sources that are citable and auditable are particularly important here. This is the only way to ensure the quality and traceability of the responses. With this integrated database, AI can decide on transparent and tailored decisions that are specific to service use cases.   <\/p><\/div><\/div><\/div><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/details>\n\t\t\t\t\t\t<details id=\"e-n-accordion-item-2481\" class=\"e-n-accordion-item\" >\n\t\t\t\t<summary class=\"e-n-accordion-item-title\" data-accordion-index=\"2\" tabindex=\"-1\" aria-expanded=\"false\" aria-controls=\"e-n-accordion-item-2481\" >\n\t\t\t\t\t<span class='e-n-accordion-item-title-header'><h4 class=\"e-n-accordion-item-title-text\"> How does SDI calculate the confidence score, source citation, and audit trail for each response? <\/h4><\/span>\n\t\t\t\t\t\t\t<span class='e-n-accordion-item-title-icon'>\n\t\t\t<span class='e-opened' ><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-minus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t\t<span class='e-closed'><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-plus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H272V64c0-17.67-14.33-32-32-32h-32c-17.67 0-32 14.33-32 32v144H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h144v144c0 17.67 14.33 32 32 32h32c17.67 0 32-14.33 32-32V304h144c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t<\/span>\n\n\t\t\t\t\t\t<\/summary>\n\t\t\t\t<div role=\"region\" aria-labelledby=\"e-n-accordion-item-2481\" class=\"elementor-element elementor-element-5414f61 e-con-full e-flex e-con e-child\" data-id=\"5414f61\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-1e5ed46 elementor-widget elementor-widget-text-editor\" data-id=\"1e5ed46\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><p>SDI uses a central knowledge base that always provides <strong>source citations<\/strong> for its answers. In addition, a <strong>hypothesis test<\/strong>is <strong>performed<\/strong>to ensure the quality of the results. An <strong>immutable audit trail<\/strong> ensures transparency and traceability of decisions and meets the requirements of the AI Act.  <\/p><\/div><\/div><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/details>\n\t\t\t\t\t\t<details id=\"e-n-accordion-item-2482\" class=\"e-n-accordion-item\" >\n\t\t\t\t<summary class=\"e-n-accordion-item-title\" data-accordion-index=\"3\" tabindex=\"-1\" aria-expanded=\"false\" aria-controls=\"e-n-accordion-item-2482\" >\n\t\t\t\t\t<span class='e-n-accordion-item-title-header'><h4 class=\"e-n-accordion-item-title-text\"> How can I tell if my installed base is \"SDI-ready\"? <\/h4><\/span>\n\t\t\t\t\t\t\t<span class='e-n-accordion-item-title-icon'>\n\t\t\t<span class='e-opened' ><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-minus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t\t<span class='e-closed'><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-plus\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M416 208H272V64c0-17.67-14.33-32-32-32h-32c-17.67 0-32 14.33-32 32v144H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h144v144c0 17.67 14.33 32 32 32h32c17.67 0 32-14.33 32-32V304h144c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z\"><\/path><\/svg><\/span>\n\t\t<\/span>\n\n\t\t\t\t\t\t<\/summary>\n\t\t\t\t<div role=\"region\" aria-labelledby=\"e-n-accordion-item-2482\" class=\"elementor-element elementor-element-cca8e05 e-con-full e-flex e-con e-child\" data-id=\"cca8e05\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7504c5c elementor-widget elementor-widget-text-editor\" data-id=\"7504c5c\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><div data-faq-a=\"\" data-pm-slice=\"2 2 [\"><p>Your installed base is \u201cSDI-ready\u201d when your systems and the underlying database enable integration with <strong>Service Decision Intelligence (SDI)<\/strong>. To achieve this, several key requirements must be met: These include <strong>data sovereignty<\/strong> on your own cloud infrastructure, the consolidation of relevant data from IoT, ERP, and CRM systems, as well as a clearly structured asset hierarchy and documented service history. The main goal is to build a reliable knowledge base that enables AI agents to make transparent and traceable service decisions that can also be cited.  <\/p><\/div><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/details>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>We have implemented a platform that centrally bundles all information on products, customers and their current orders. Customers have access to all important documents relating to the products, from technical documentation, brochures, videos, certificates, product descriptions and operating instructions to a digital twin for the current generation of machines. A spare parts store is also integrated into the portal.<\/p>\n","protected":false},"author":5,"featured_media":39486,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[43054],"tags":[],"class_list":["post-39498","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-and-automation"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/posts\/39498","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/comments?post=39498"}],"version-history":[{"count":19,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/posts\/39498\/revisions"}],"predecessor-version":[{"id":42569,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/posts\/39498\/revisions\/42569"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/media\/39486"}],"wp:attachment":[{"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/media?parent=39498"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/categories?post=39498"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.logicline.de\/en\/wp-json\/wp\/v2\/tags?post=39498"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}