Development of an AI Platform based on Microsoft Azure
Secure and scalable AI usage in the company is created through a central Enterprise Search that bundles information from systems such as SharePoint, ServiceNow, and SAP.
1x Cloud Engineer 2x AI Engineers 1x Developer 1x Project Manager
ongoing since December 2024
Our Impact
Governance by Design
Compliant from day one
Self-Service for Business
Fast access without security risks
Enterprise-ready AI
Enterprise search across various business units instantly available
The Challenge
Without a central platform, isolated AI experiments by individual teams create significant shadow IT risks and a lack of standards for data privacy, compliance, and cost control. At the same time, enterprise knowledge is fragmented across different systems like SharePoint, ServiceNow, and SAP, leading to inefficient search processes and time loss. Furthermore, the lack of clarity regarding the optimal selection and costs of specific LLM models complicates the targeted implementation of AI use cases.
The Solution
We designed and implemented an enterprise-wide AI platform based on Azure AI Foundry and AI Factory. The architecture allows all business units to securely use AI services – with central governance, uniform guardrails, and full cost transparency. The platform was built according to the "Secure by Default" principle: Private Endpoints, Entra ID integration, role-based access control, and Azure Policies ensure that compliance requirements are automatically met.
Before implementation, we conducted extensive benchmarks: Different LLM models - including Azure OpenAI GPT variants and Microsoft Copilot - were tested for response quality, latency, cost, and suitability for the specific use cases. The results flowed directly into the architectural decisions. As the first productive solution, we developed an Enterprise Search based on LangChain. SharePoint, ServiceNow, and SAP were connected as source systems and indexed in Azure AI Search. Via a chat-based web app, employees can ask questions in natural language and receive answers from all connected systems – with source citations and taking existing permissions into account. The result: A scalable AI platform with well-founded model selection and an immediately noticeable added value – enterprise knowledge accessible in seconds, based on the optimal LLM for the respective use case.
Ready for your Success Story?
Let's make your next project a success together. Contact us for a non-binding initial consultation.