Case Study Snapshot
The table below summarizes the key facts about Dlubal’s AI deployment at a glance, providing a quick reference for the scale, scope, and outcomes of the implementation.
| Field | Details |
|---|---|
| Company | Dlubal Software |
| Industry | Structural Analysis & Design Software |
| Use Case | AI Customer Support, Technical Knowledge Base, In-App Assistant |
| Users Supported | 130,000+ |
| Countries Served | 132 |
| Languages Supported | 10 |
| Platform | CustomGPT.ai |
| Deployment Locations | dlubal.com (website chatbot) + inside Dlubal desktop software products |
| Key Outcomes | 24/7 support coverage, faster response times, increased customer satisfaction, reduced repetitive ticket escalations, improved support team efficiency |
Executive Summary
Dlubal Software, a global leader in structural analysis and design software used by engineers across 132 countries, faced a challenge familiar to every fast-scaling technical software company: how to deliver fast, accurate, round-the-clock customer support to a global user base without proportionally growing a highly specialized support team.
The answer was Mia, an AI knowledge base assistant built on CustomGPT.ai, deployed both on dlubal.com and embedded directly inside Dlubal’s desktop products. Mia now serves over 130,000 users worldwide, handling everything from complex structural calculation queries and licensing questions to billing support, instantly, accurately, and in multiple languages, 24 hours a day, seven days a week.
The result: measurably faster response times, significantly higher customer satisfaction scores, a reduction in repetitive ticket escalations to human engineers, and a scalable foundation for continued AI expansion across Dlubal’s product and marketing functions.
Company Overview
Dlubal Software is a family-founded and operated company headquartered in southern Germany, with technical development offices in Prague, Czech Republic, and commercial offices across the United States and beyond. For over 35 years, Dlubal has built precision structural engineering software trusted by more than 13,000 companies and 130,000+ individual users across 132 countries.
Their flagship products, RFEM and RSTAB, are considered industry standards in structural analysis and finite element modelling, used by civil and structural engineers on projects ranging from bridges and high-rises to industrial facilities and complex infrastructure.
Given the technical depth of the product, Dlubal’s support function has always required expert-level knowledge. Users ask questions that go well beyond standard software troubleshooting. They need help interpreting structural calculations, understanding load combinations, navigating regulatory compliance, and applying domain-specific engineering logic. This is support that cannot be handled by a generic FAQ page or a basic chatbot.
Dlubal’s AI strategy is led by Prof. Dr. Michael Kraus, an expert in machine learning and deep learning, working in close collaboration with founder and CEO Georg Dlubal, AI specialist Dogukan Karatas, and the broader AI team.
The Challenge: Supporting 130,000 Engineers at Scale
A Global User Base With Complex, Specialized Needs
Engineering software support is not a commodity problem. When a structural engineer in Tokyo submits a support ticket at 11 PM local time, they are likely troubleshooting a multi-story building load model that is blocking a project deadline. The stakes are high, the questions are technical, and the answers need to be precise.
Dlubal’s support engineers were fielding an enormously broad range of inquiries:
- Technical questions about structural calculations, finite element analysis, load cases, and result interpretation
- Software bug reports and version-specific behavior questions
- Licensing and activation issues across a global install base
- Billing and account management requests
- Onboarding queries from new users navigating a feature-rich, technically complex product
The breadth of these queries, combined with the global distribution of Dlubal’s user base across many time zones, made consistent 24/7 coverage structurally difficult. Hiring specialized support engineers at the scale needed to cover every region and every hour of the day was neither economically viable nor operationally practical given the engineering talent market.
Why Traditional Support Was Not Scalable
Traditional support channels, email tickets, phone support, and static FAQ pages, were simply not designed for the volume, complexity, or time-zone diversity of Dlubal’s support demands. Several specific bottlenecks had become critical:
- Talent scarcity: Finding support engineers with deep expertise in structural analysis software is difficult in any market. Dlubal could not simply hire its way out of the problem.
- Time-zone gaps: With users across North America, Europe, Asia, and beyond, no single support team configuration could offer genuine around-the-clock coverage without significant operational cost.
- Repetitive ticket overhead: A meaningful portion of incoming tickets covered questions already answered in Dlubal’s extensive documentation, but that documentation was vast, technical, and difficult for users to navigate quickly.
- Inconsistent answer quality: Without a centralized knowledge delivery system, answer quality could vary depending on which support engineer responded, their area of expertise, and the complexity of the specific question.
- Failed internal prototype: Dlubal’s AI team had previously attempted to build an internal Retrieval-Augmented Generation (RAG) prototype. While promising in concept, it stalled when the team tried to scale it, hitting technical limits in accuracy, multilingual handling, and integration capability.
The following table maps each core business challenge to the specific CustomGPT.ai solution that addressed it, and explains why it mattered to the business.
Challenge vs. Solution
| Business Challenge | Why It Mattered | CustomGPT.ai Solution |
|---|---|---|
| No 24/7 support coverage across global time zones | Engineers worldwide needed instant answers outside business hours | AI assistant Mia deployed on website and in-app, available around the clock |
| Talent scarcity for specialized engineering support roles | Qualified support engineers are rare and expensive to recruit and retain | AI handles high-volume, documented queries so human experts focus on complex issues |
| Repetitive tickets consuming expert engineering time | Skilled engineers spent hours answering questions already in documentation | Anti-hallucination AI grounded in official docs intercepts and resolves known queries automatically |
| Inconsistent answer quality across support team | User experience varied depending on who responded and when | Single AI knowledge base delivers consistent, citation-backed answers every time |
| Internal RAG prototype failed to scale | Poor accuracy and multilingual gaps meant the prototype could not serve production traffic | CustomGPT.ai’s enterprise platform provided production-grade accuracy, multilingual support, and deep API access |
| Multilingual coverage across 132 countries | Users expect support in their native language | REST API-based language switching serves 10 languages from one knowledge base |
Why Dlubal Chose CustomGPT.ai
Vendor Evaluation: Quality, Security, and API Depth
The Dlubal AI team conducted a thorough vendor evaluation before selecting CustomGPT.ai. As Prof. Dr. Michael Kraus explained:
“We looked at different vendors and in the end, we chose CustomGPT.ai because for us, it had the best spectrum of quality of answers, ease of use, scalability, and most importantly, API capabilities. We have many internal processes that rely on an automated connection to CustomGPT.ai and its API offers great value.”
Four criteria drove the final decision:
- Answer quality and anti-hallucination controls: For an engineering software company, factual accuracy is non-negotiable. A structural engineer acting on incorrect AI-generated guidance faces real professional and safety consequences. CustomGPT.ai’s grounding mechanism, which tightly constrains the LLM to only answer from ingested source documents, was a decisive factor.
- API depth and extensibility: Dlubal did not just want a chatbot on a webpage. They needed an AI layer that could be woven into their existing software products and internal workflows via robust REST API access. CustomGPT.ai’s API architecture provided exactly that flexibility.
- Multilingual capability: Serving engineers in over 130 countries requires genuine multilingual support. CustomGPT.ai’s platform supported language switching at the API level, enabling Dlubal to serve users in ten languages from a single deployment.
- Security and data controls: Enterprise-grade data security was a baseline requirement. CustomGPT.ai’s GDPR-compliant, SOC2-certified infrastructure met Dlubal’s standards for handling proprietary technical documentation.
Implementation Process
From Decision to Deployment: A Two-Week Sprint
After selecting CustomGPT.ai, the Dlubal AI team moved quickly. The implementation unfolded across several focused phases:
Phase 1: Data Ingestion The team uploaded Dlubal’s extensive knowledge corpus into the CustomGPT.ai no-code platform. This included:
- Product manuals in JSON and PDF formats
- Comprehensive e-learning guides and tutorial content
- Full sitemap ingestion to capture web-based documentation
- Technical reference materials covering structural analysis workflows
Phase 2: Persona Tuning Over an intensive two-week sprint, the team fine-tuned the AI assistant’s behavior, tone, and output formatting. Key calibration work included:
- Ensuring mathematical formulas and structural engineering expressions rendered correctly in responses
- Configuring language-switching behavior via REST API override, enabling the web widget to serve users in their preferred language automatically
- Tuning the assistant’s tone to match Dlubal’s professional, technically precise voice
Phase 3: Dual Deployment Mia was deployed in two distinct contexts:
- On dlubal.com, as a publicly accessible AI support assistant for website visitors and existing users
- Inside Dlubal’s desktop software products, providing contextual in-app assistance exactly where users encounter questions during active engineering work
Phase 4: Continuous Improvement Loop Following launch, the team established a systematic feedback process. Weekly reviews of chat logs were supplemented by a real-time like/dislike signal attached to every AI response. Patterns in negative feedback sometimes indicated users were running outdated product versions, giving Dlubal’s sales team the opportunity to proactively reach out about upgrades.
The table below details the specific CustomGPT.ai capabilities Dlubal deployed, how each was applied, and the business value it delivered.
Technical Implementation
| Capability | How Dlubal Used It | Business Value |
|---|---|---|
| No-Code Builder | Configured Mia’s knowledge base, persona, and deployment settings without developer resources | Rapid deployment in a two-week sprint with no engineering bottleneck |
| Anti-Hallucination Technology | Grounded all LLM responses strictly within ingested Dlubal documentation | Prevented fabricated answers in a high-stakes technical domain where accuracy is critical |
| Data Connectors (JSON, PDF, Sitemap) | Ingested product manuals, e-learning guides, and full website documentation | Single unified knowledge base covering the full depth of Dlubal’s product content |
| REST API | Embedded Mia inside Dlubal desktop software; enabled multilingual language-switching override | In-app contextual assistance and true multilingual delivery from one deployment |
| Security Controls (GDPR, SOC2) | Applied enterprise-grade data handling to proprietary technical documentation | Compliance confidence for a global enterprise software company |
| Feedback and Analytics | Weekly chat log reviews plus real-time per-response like/dislike ratings | Continuous quality improvement and proactive sales intelligence from support patterns |
AI Assistant Capabilities: What Mia Can Do
Mia is not a generic chatbot. It is a domain-specific engineering AI assistant built on Dlubal’s own intellectual property and trained exclusively on verified company documentation. Its capabilities span the full range of Dlubal’s support surface:
Technical Support
- Answers detailed questions about RFEM and RSTAB structural analysis workflows
- Explains load case configurations, result interpretation, and finite element modelling concepts
- Provides cited responses drawn directly from Dlubal’s official product documentation
Administrative Support
- Handles licensing, activation, and account management queries
- Resolves billing and subscription questions without escalation
- Routes complex issues to the appropriate human support channel when needed
In-App Contextual Help
- Embedded directly inside Dlubal’s desktop products, Mia delivers contextual guidance at the exact moment a user encounters a question, dramatically reducing friction and support ticket volume
Multilingual Delivery
- Serves users in ten languages, with language detection and switching managed via REST API
- Enables consistent support quality for Dlubal’s international customer base regardless of region
Knowledge Citations
- Every Mia response includes citations linking back to source documentation, giving engineers confidence to trust and verify the information they receive
Results and Business Impact
24/7 Support, Zero Additional Headcount
The most immediate and measurable outcome of Mia’s deployment is the delivery of genuine around-the-clock technical support to Dlubal’s global user base without a corresponding increase in support staff. Users in any time zone can now get fast, accurate answers to both technical and administrative questions at any hour.
The table below summarizes the specific, documented outcomes Dlubal achieved across key support dimensions after deploying CustomGPT.ai.
Before vs. After CustomGPT.ai
| Support Area | Before CustomGPT.ai | After CustomGPT.ai |
|---|---|---|
| Support availability | Business hours only; limited time-zone coverage | 24/7, across all time zones, 365 days a year |
| Response time | Hours for ticket-based responses from human engineers | Instant AI-generated answers with source citations |
| Language coverage | Limited by human team language skills | 10 languages served from a single knowledge base deployment |
| Repetitive ticket handling | Escalated to human engineers regardless of complexity | Intercepted and resolved automatically by Mia |
| Answer consistency | Variable, depending on engineer expertise and availability | Consistent, documentation-grounded answers every interaction |
| User access to help | Website only; users had to leave software to seek support | Website and in-app, with contextual help inside the product |
| Support team focus | Split between routine queries and complex problems | Focused on genuinely complex, novel engineering issues |
| Sales intelligence | No signal from support interactions | Negative feedback patterns surface outdated-version users for proactive outreach |
Results Summary
The following table consolidates the key business outcomes Dlubal achieved, providing a concise reference for the measurable impact of the CustomGPT.ai deployment.
| Outcome | Result |
|---|---|
| 24/7 support availability | Achieved across all time zones without headcount expansion |
| Response speed | Reduced from hours (ticket queue) to instant AI-generated answers |
| Customer satisfaction | Noticeable increase, per CEO Georg Dlubal |
| Repetitive ticket reduction | Documented queries intercepted by AI before reaching human engineers |
| Support team efficiency | Significant increase, with engineers refocused on high-complexity issues |
| Multilingual coverage | 10 languages served from one knowledge base across 132 countries |
| Users supported | 130,000+ engineers and website visitors |
| Sales intelligence | Feedback patterns generate proactive outreach opportunities for outdated-version users |
Faster Response Times and Higher Customer Satisfaction
According to Georg Dlubal, the AI assistant has produced a “noticeable increase in customer satisfaction” alongside faster response delivery. Support interactions that previously required a support engineer to research, compose, and send a reply, a process that could take hours, are now resolved in seconds by Mia.
Elimination of Repetitive Ticket Escalations
A significant share of incoming support tickets covered questions already documented in Dlubal’s knowledge base. Mia now intercepts this category of query entirely, preventing it from ever reaching a human support engineer. The result is a measurable increase in support team efficiency, with skilled engineers freed to focus on genuinely complex, novel problems that require human expertise.
Multilingual Support: Engineering Without Language Barriers
One of the most strategically significant aspects of Mia’s deployment is its multilingual AI customer support capability. With Dlubal’s products used by engineers across 132 countries, language coverage is not a nice-to-have; it is a core support requirement.
CustomGPT.ai’s platform enabled Dlubal to implement dynamic language detection and switching via REST API, meaning Mia automatically recognizes the user’s preferred language and responds accordingly. The assistant currently operates in ten languages, providing native-quality technical responses across Dlubal’s major markets.
This capability eliminates a chronic inefficiency in traditional multilingual support models: the need to maintain separate localized knowledge bases, separate support queues, or separate vendor relationships for different language markets. With Mia, a single AI knowledge base delivers consistent, accurate, multilingual support from one platform.
Customer Voice
“The assistant has enabled us to offer 24/7 support while improving accuracy and speed of response. This has led to a noticeable increase in customer satisfaction and even faster support. At the same time, our support team has seen a significant increase in the efficiency of our customer service.”
Georg Dlubal, CEO, Dlubal Software
“We looked at different vendors and in the end, we chose CustomGPT.ai because for us, it had the best spectrum of quality of answers, ease of use, scalability, and most importantly, API capabilities. We have many internal processes that rely on an automated connection to CustomGPT.ai and its API offers great value.”
Prof. Dr. Michael Kraus, AI Expert, Dlubal Software
“We saw some of the issues and we were always in an open dialogue, especially with Eli. What really is a great plus, and it’s also the opinion of our CEO, is that you provided constantly really quick and very nice support.”
Prof. Dr. Michael Kraus, AI Expert, Dlubal Software
Future Expansion Plans
Mia’s current deployment, spanning website support and in-app assistance, is only the beginning of Dlubal’s AI strategy. The team has already identified the next phase: AI-powered marketing applications, using CustomGPT.ai to support content delivery, lead engagement, and knowledge-driven marketing workflows.
Looking further ahead, Dlubal and CustomGPT.ai are actively exploring expanded generative AI capabilities. The Dlubal team is particularly interested in voice and image-based AI functionality, capabilities that could enable Mia to analyze structural rendering images submitted by engineers, or deliver spoken step-by-step guidance within the software interface.
Key Takeaways
For SaaS leaders and enterprise AI buyers evaluating AI support automation, the Dlubal implementation demonstrates several transferable lessons:
- 24/7 technical support is achievable without proportional headcount growth when the AI is trained on proprietary domain knowledge, not generic web data.
- Anti-hallucination controls are essential in technical domains. General-purpose LLMs are insufficient for high-stakes engineering support without document grounding.
- In-app AI deployment outperforms standalone chatbots. Meeting users inside their workflow context dramatically improves adoption and reduces ticket volume.
- Multilingual AI at scale is a solved problem. With the right platform, a single knowledge base can serve a global user base across ten or more languages.
- Feedback loops compound AI quality over time. Real-time rating signals and regular log reviews turn deployment into a continuous improvement system.
- Vendor partnership quality matters. Fast, technically knowledgeable support during implementation accelerates time-to-value and reduces rollout risk.
Frequently Asked Questions
What is an AI customer support assistant for engineering software?
An AI customer support assistant for engineering software is a specialized AI agent trained on a company’s proprietary product documentation, manuals, and knowledge base. Unlike generic chatbots, it answers domain-specific technical questions, such as structural calculation methods, software configuration, or engineering workflow guidance, with cited, accurate responses grounded in verified source material. Dlubal’s AI assistant Mia, built on CustomGPT.ai, is an example serving over 130,000 structural and civil engineers.
How does CustomGPT.ai prevent AI hallucinations in technical support?
CustomGPT.ai uses a document-grounding architecture that restricts the underlying language model to only generating responses based on ingested source documents. It does not draw on general internet knowledge or speculation. Every answer Mia provides is cited and traceable back to Dlubal’s official documentation, ensuring engineers receive accurate, verifiable information rather than fabricated responses.
Can an AI chatbot support multilingual engineering customers?
Yes. CustomGPT.ai’s platform supports multilingual AI customer support through language detection and REST API-based language switching. Dlubal’s Mia assistant currently serves engineers in ten languages from a single knowledge base deployment, enabling consistent support quality across Dlubal’s 132-country user base without maintaining separate localized systems.
How did Dlubal embed an AI assistant inside its desktop software?
Dlubal used CustomGPT.ai’s REST API to integrate Mia directly into its desktop structural analysis products. This required approximately one week of technical integration work to resolve widget sizing constraints and configure language-override behavior. The result is a contextual in-app AI assistant that delivers guidance to engineers within their active working environment, without requiring them to leave the application.
What types of questions does Dlubal’s AI assistant handle?
Mia handles a broad range of both technical and administrative queries, including structural analysis methodology questions, load case configuration guidance, result interpretation, software bug reporting triage, licensing and activation support, billing and account management, and onboarding assistance for new users. Truly complex or novel issues are routed to human support engineers.
How does Dlubal use AI feedback signals to improve support quality?
Dlubal implemented a continuous improvement workflow combining weekly chat log reviews with a real-time per-response like/dislike rating system. Patterns in negative feedback surface documentation gaps, user confusion points, and signals about outdated software versions in use, enabling both support quality improvements and proactive sales outreach.
How long did it take to deploy the AI assistant?
After vendor selection, the core Mia assistant was configured and deployed within approximately two weeks. This sprint covered data ingestion (manuals, e-learning content, sitemap), persona tuning, formula rendering calibration, and multilingual configuration. The in-app software integration required an additional focused technical effort of approximately one week.
Why did Dlubal choose CustomGPT.ai over other AI vendors?
According to Prof. Dr. Michael Kraus, Dlubal’s AI expert, the decision came down to four factors: the quality and accuracy of AI-generated answers, ease of platform use and no-code deployment capability, scalability to serve a global user base, and most importantly the depth and flexibility of CustomGPT.ai’s API. The API capability was critical because Dlubal required deep integration with its own internal processes and software products.
What business results did Dlubal achieve with AI support automation?
Dlubal achieved 24/7 technical and administrative support coverage for over 130,000 users without expanding its support headcount, a measurable increase in customer satisfaction scores, faster average response times, a significant reduction in repetitive ticket escalations to human engineers, and improved support team efficiency. The feedback loop also generated actionable sales intelligence identifying users on outdated product versions.
What industries can benefit from AI support automation similar to Dlubal’s implementation?
Any technical software company serving a large, globally distributed user base with complex domain-specific support needs is a strong candidate. Industries particularly well-suited include engineering software (civil, structural, mechanical), scientific computing platforms, financial software, legal technology, medical device software, and industrial automation tools, anywhere where answer accuracy is critical and support queries require deep domain knowledge.
Ready to Scale Technical Support Without Scaling Your Team?
Dlubal serves 130,000 engineers in 132 countries with a single AI assistant trained on its own documentation. If your company is facing the same pressure, a global user base, complex technical queries, and the impossibility of 24/7 human coverage, CustomGPT.ai can help you build the same capability.
CustomGPT.ai delivers:
- AI trained exclusively on your documentation, no generic web data, no hallucinations
- Anti-hallucination architecture with citation-backed responses
- Multilingual support from a single knowledge base
- Deep REST API integration for in-app and workflow embedding
- No-code deployment with enterprise-grade security (GDPR, SOC2)
- Continuous improvement tools including feedback signals and analytics
Start your free 7-day trial Talk to enterprise sales
To learn more about Dlubal Software, visit dlubal.com. For partnership inquiries, contact Daniel Dlubal at daniel.dlubal@dlubal.com.
Read more CustomGPT.ai customer success stories at customgpt.ai/customers.
