← Back to Deutscher Maklerverbund's multi-agent AI platform triggers system actions in 70% of broker conversations

Source proof for Deutscher Maklerverbund's multi-agent AI platform triggers system actions in 70% of broker conversations

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

12 fields supported

Title

Deutscher Maklerverbund's multi-agent AI platform triggers system actions in 70% of broker conversations

derived · high
…ctions. More importantly, PWX is being used to carry out core operational work. Around 70% of conversations trigger at least one system action—such as retrieving data, initiating a process, or preparing documentation. Instead of just asking questions, brokers are executing tasks directly within t…

Description

DEMV Deutscher Maklerverbund, a German insurance broker network serving more than 7,000 offices and 16,000 users, built Professional Works X (PWX), a multi-agent AI platform using Azure OpenAI Service, Microsoft Foundry, and Azure API Management. Each PWX agent manages a specific task area -- drafting communications, handling policy and claims operations -- allowing brokers to interact via chat or voice and submit claims, manage policies, and capture customer information directly through AI-powered processes, such as creating a claim from an uploaded photo of a police accident report. After a roadshow launch, weekly active PWX users grew about 65%, from around 850 to 1,400, with the platform handling 700-800 chats daily (peaking around 1,000) and about 70% of conversations triggering at least one system action such as retrieving data or preparing documentation.

derived · high
…Germany. Adoption, usage, and real operational impact After a roadshow launch, weekly active PWX users grew by approximately 65%, from around 850 to 1,400. PWX is now used each week by around 19–20% of active Professional Works users,…

Company

DEMV Deutscher Maklerverbund

quote · high
…exity—all within one of Europe’s most tightly regulated financial environments. DEMV Deutscher Maklerverbund (DEMV) is a Germany-based broker network providing product access, software, and services to independent brokers. Its “Professional Works” platform supports more than 7,000 offices and 16,000 u…

Country

Germany

classification · high
…in Foundry Models Azure SERVICES AND SUPPORT ORGANIZATION SIZE 50-999 employees COUNTRY/REGION Germany BUSINESS NEED AI and Agents INDUSTRY Financial Services Share the story Explore…

Industry

Financial Services

classification · high
…ZATION SIZE 50-999 employees COUNTRY/REGION Germany BUSINESS NEED AI and Agents INDUSTRY Financial Services Share the story Explore related stories /h2> "> Explore related stories Stories…

Problem

Insurance brokers faced rising expectations for faster, more proactive service within one of Europe's most tightly regulated financial environments, and DEMV's feature-rich 'Professional Works' platform, supporting more than 7,000 offices and 16,000 users, grew increasingly complex as adoption increased.

derived · high
…etwork providing product access, software, and services to independent brokers. Its “Professional Works” platform supports more than 7,000 offices and 16,000 users, connecting contracts, customers, insurers, and processes in one place. As adoption increased, the scope and sophistication of broker workflows grew in…

Solution

DEMV built Professional Works X (PWX) using Azure OpenAI Service, Microsoft Foundry, and Azure API Management, creating a coordinated multi-agent platform where each agent manages a specific task area, using a hybrid cloud approach that kept core systems of record in place while AI orchestration, reasoning, and interaction were built in Azure.

derived · high
…multi-agent evolution of its platform took shape as Professional Works X (PWX). Built using Azure OpenAI Service , Microsoft Foundry (formerly Azure AI Foundry), and Azure API Management , each PWX agent manages a specific task area, from drafting communications to handling policy and claims operations. Brokers interact with the system through chat or voice, allowing them to focus…

Business value

After a roadshow launch, weekly active PWX users grew about 65%, from around 850 to 1,400, with the platform supporting 700-800 chats per day (peaking around 1,000), and about 70% of conversations triggering at least one system action, freeing brokers for higher-value work.

derived · high
…ctions. More importantly, PWX is being used to carry out core operational work. Around 70% of conversations trigger at least one system action—such as retrieving data, initiating a process, or preparing documentation. Instead of just asking questions, brokers are executing tasks directly within t…

AI capabilities

Agentic AI, Conversational AI, Natural Language Processing

classification · high
…sk area, from drafting communications to handling policy and claims operations. Brokers interact with the system through chat or voice, allowing them to focus on outcomes rather than navigating complex processes. As adoption has grown, PWX has expanded from assisting with tasks to executing…

Technology

Azure OpenAI Service, Microsoft Foundry, Azure API Management

classification · high
…cher Maklerverbund. Discover more details CUSTOMER DEMV Deutscher Maklerverbund PRODUCTS Microsoft Foundry Azure API Management Azure OpenAI in Foundry Models Azure SERVICES AND SUPPORT ORGANIZATION SIZE 50-999 employees COUNTRY/REGION Germany…

Headline outcome

derived · high
…ctions. More importantly, PWX is being used to carry out core operational work. Around 70% of conversations trigger at least one system action—such as retrieving data, initiating a process, or preparing documentation. Instead of just asking questions, brokers are executing tasks directly within t…

Use case type

Workflow automation

classification · high
…us on outcomes rather than navigating complex processes. As adoption has grown, PWX has expanded from assisting with tasks to executing end-to-end workflows. Brokers can submit claims, manage policies, and capture customer information di…
Capture details
Captured
15 Sept 2026, 08:17 UTC
Extractor
fetch-strip@1
Snapshot hash
6cda47e7d9e55c6e47858ac3a03411062175a8e9c676a81b33e1ff64dd4c56cb