We use cookies and other technologies on our website to make the use of our website more attractive, user-friendly and effective. We use technically necessary cookies to guarantee the error-free functionality of our website. In addition, we use cookies and other technologies to optimize our website and marketing efforts. For example, we monitor the success of our campaigns with the help of tracking tools. Click "Allow All" to save all saved cookies. You can change your cookie settings at any time. Details are available here: Data Privacy Notice.
General
When you visit our website, cookies and other technologies store and read information on your device. This also includes personal data such as your IP address. Information about your browser, settings and device can also be retrieved.
We use this information to provide you with a graphically accurate display and user-friendly operation of the website. We also use this information to optimize our marketing activities and our online presence.
More information about the individual cookies and technologies is available under the corresponding tabs as well as in our Data Privacy Notice.
These cookies are necessary to provide error-free content and for the technical performance of the website. These are used to control specific functions on the website and make them available to you. These cookies are necessary for visiting the website and cannot be deselected.
Analysis
We use various cookies and technologies on our website to analyze visitor behavior, such as the length of time spent on our website. We use the services of Google Analytics for this analysis.
Google Analytics collects and stores visitor data such as IP address, time of visit, referrer URL and information about your browser and operating system. Google stores this data for a maximum of 14 months. The collected data may be summarized by Google in a profile that is assigned to you or your device.
More information about our use of Google Analytics is available in our Data Privacy Notice.
We would like to inform you explicitly that the collected data will be transmitted to the United States if you consent to this process.
The level of data privacy in the USA is lower than in EU countries. This means that there is a risk that your data may be accessed by a U.S. government agency (intelligence agencies, for example) if it invokes the appropriate legal remedy.
To protect your data from our site as much as possible, we use Google's IP anonymization. By agreeing to the use of Google Analytics, you consent to the transfer of data to the USA pursuant to Art. 49 para. 1 lit. a) GDPR and are aware of the risks of such a transfer. The legal basis for the processing of this data is Art. 6 para. 1 lit. a) GDPR (consent).
You can change your settings at any time. More information about Google Analytics and its data privacy is available at: https://policies.google.com/technologies/cookies
Marketing
We use the conversion tracking feature of LinkedIn to better customize our advertising offers and campaigns. This conversion tracking is enabled by the LinkedIn Insight Tag. This collects user data from your device, including the URL, the referrer URL, the device properties, the browser properties, and the IP address. Your data will be pseudonymized by LinkedIn within seven days and deleted within 180 days. The personal data collected is not shared with us, we only receive anonymous reports on the demographics of our target audience and the performance of our ads.
Your data will only be transmitted after your consent pursuant to Art. 6 para. 1 lit. a) GDPR.
More information about LinkedIn Conversion Tracking is available in our Data Privacy Notice.
So...
are we doing AI
or not?
Large Language
Models in
Contract Management
Vitesco Technologies
Project in a nutshell
-
Prompting forward. Generative AI in an innovative e-mobility company? Makes sense. In a dedicated use case, Vitesco Technologies explored whether Large Language Models (LLMs) could automate and improve their complex contract review process.
The Customer Need
-
More efficiency in contract handling. Quick insights instead of drawn-out analysis. As part of a broader process optimization effort, we defined the use case “Automated Contract Analysis.” Vitesco Technologies wanted to find out if AI could simplify the demanding legal contract reviews. At that time, the company had no hands-on experience with AI—plus, the data involved was highly sensitive. Choosing the right LLM was critical. After thorough assessments and tests, the open-source model Mistral was selected in October 2023.
Challenges & Extra Miles
-
Missing standards & benchmarks. Contracts come in many forms—with varied structures, layouts, and contexts. Our first challenge was to use an LLM to develop a structure that made these contracts machine-readable and analyzable.
Innovation
-
The smart contracting recipe. Start with a vector database (Qdrant), add a large language model, a dedicated user interface, and blend it all with compressed expert knowledge – deployed via a trusted hyperscaler. Then comes the real magic: custom AI training to inject industry-specific knowledge tailored to Vitesco Technologies.
-
The result? A smart tool that:
-
Stores domain-specific company knowledge
-
Is accessible to all expert users
-
Filters and displays contracts effectively
-
Features semantic search to detect special clauses in legacy contracts
-
Enables chatbot-style interactions via Natural Language Processing (NLP)
-
Offers personalized contract overviews
-
Flags risky clauses to mitigate legal exposure
-
Includes an admin panel for custom settings
-
Supports structured search across supplier/customer contracts
Big
Wins
-
Laying the claim. Just a short while ago, generative AI was still a frontier for most of us. Vitesco Technologies approached it with curiosity and courage. Today, their contract management team has become the company’s go-to unit for all things GenAI.
-
1Up to 80% reduction in contract review time
-
2Less than 3 months to MVP completion
-
340.000 + contracts now integrated into the solution
Small Victories
-
Prompt Engineering Training. LLMs live on prompts. But what makes a prompt “work”? Our expert delivered training to establish foundational understanding, equipping Vitesco’s teams to better evaluate and craft future AI use cases.
-
Better done than perfect. The “fail forward” mindset often beats perfectionism. It takes a cultural shift - but once that’s in place, like here, results start coming fast.
Next Steps &
Future Upgrades
-
Always room for better. Next up? Features like automatic clause rewording, contract comparisons with previous versions, and expanded use cases as token limits evolve. This flexible setup means many more applications can be built with just minor tweaks.
-
"The potential of generative AI is enormous. At Vitesco Technologies, we saw real opportunities, especially in contract management. This use-case-driven approach helped us take strong first steps. The insights we’ve gained on LLMs, prompting, and automation are now driving AI adoption across the entire company."
-
Alina Stahl, Head of Contract Management bei Vitesco Technologies
Large Language Models
in Contract Management
-
blu BEYOND GmbH
Keltenring 11,
82041 Oberhaching
