{"slug":"roland-berger-cuts-knowledge-search-response-times-to-8-seconds-with-graph-based-ai-agents-on-azure","url":"https://findausecase.com/use-cases/roland-berger-cuts-knowledge-search-response-times-to-8-seconds-with-graph-based-ai-agents-on-azure","title":"Roland Berger cuts knowledge-search response times to 8 seconds with graph-based AI agents on Azure","description":"Roland Berger redesigned its internal Knowledge Hub using graph-based, reasoning-acting AI agents built on Azure AI Search, Azure OpenAI, Azure AI Document Intelligence and Azure Databricks. The multi-agent system reduced average response times for complex, multi-source consulting knowledge queries to 8 seconds, with citations included, and is now used by around 70 percent of the firm's workforce.","company":"Roland Berger","industry":"Professional Services","country":"Germany","aiCapabilities":["Agentic AI","Document Intelligence"],"technology":["Azure OpenAI Service","Azure SharePoint","Azure Database for PostgreSQL","Azure AI Document Intelligence","Azure AI Search","Azure Databricks","Azure Static Web Apps","Azure AI Foundry","Microsoft 365 Copilot"],"deployment":"Public Cloud","problemStatement":"For management consultants at Roland Berger, having the right information in the right place at the right time is essential, but searching through documents in huge databases and knowledge repositories for non-customer-specific information was at times laborious and time-consuming. Even its first-generation Knowledge Hub reached its limits on complex issues that involved bringing knowledge together from different sources: consultants sometimes had to ask up to three separate questions to get filtered knowledge from three different studies, and each answer came back with only its own source displayed, making it time-consuming to refer back to the documents for review.","solutionApproach":"Roland Berger redesigned its Knowledge Hub with graph-based 'reasoning acting' (ReAct) AI agents, each an expert in a different area or process, connected via a graph and sharing a process memory. The agents break natural-language user requests into individual steps, retrieve knowledge from Azure AI Search, and hand results to the agent that generates the final response, drawing on internal SharePoint pages or, depending on data classification, external sources via the Microsoft Bing API. Azure AI Document Intelligence extracts information from the various document formats feeding the data corpus, with processing parallelized through Azure Databricks; Azure Database for PostgreSQL stores user-specific information, Azure OpenAI provides the underlying AI models, users interact through an in-house interface built on Azure Static Web Apps, and quality is assured through evaluation in Azure AI Foundry.","businessValue":"Using graph-based AI agents, Roland Berger reduced average knowledge-search response times to eight seconds, with answers that include sources and citations, increasing employees' trust in generative AI; consultants now invest the hours they used to spend searching through documents in higher-value, value-adding activities, and the AI agents are already used by around 70 percent of the firm's workforce.","evidence":{"band":"high"},"sourceUrl":"https://www.microsoft.com/en/customers/story/23617-roland-berger-azure-open-ai-service","dates":{"publishedAt":"2026-10-09T05:45:25.439Z","publishedAtSource":"pipeline","updatedAt":"2026-10-09T05:45:25.439Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/roland-berger-cuts-knowledge-search-response-times-to-8-seconds-with-graph-based-ai-agents-on-azure. Bulk republication requires permission."}