← Case Studies Live Case Study

A construction group with 3 brands.
One platform. Everything visible.

Three companies under one roof: a general contractor, a natural stone distributor, a window supplier. This is what we built for them, and it's running right now. Click through the live instances below.

The Client

Three brands. One operational challenge.

A German construction group running three distinct brands, a general contractor, a natural stone distributor, and a window supplier. Each brand has its own clients, its own products, its own website. But the back office is one team.

Their problem: everything ran on email, spreadsheets, and memory. Customer requests fell through the cracks. Product catalogs were PDFs. Nobody knew what the other brand was doing.

Phase 1, Foundation

Websites that comply. Google Workspace that runs itself.

Each brand got a responsive website with full German compliance, Impressum, DSGVO privacy policy, cookie consent. Google Workspace was set up with managed users, groups, shared drives, MFA enforcement. Professional email for every team member.

Three brands. Three domains. One shared Google Workspace with organized drive structures and permission groups per brand.

Phase 2, Client Collaboration

Let clients tell you what they want.

Instead of guessing what features each brand's clients need, we built a Feature Voting Board. Clients submit feature requests in their own words. They vote on what matters most. AI turns each submission into a proper work order, with clear acceptance criteria, effort estimate, and cost projection. One click routes it to the right team.

Each brand gets its own subdomain. Clients see only their brand's board.

Live, General Contractor Feature Board

This is the actual board running on our infrastructure. Clients of the general contracting brand submit and vote on features here. Try it, submit a feature request.

Phase 3, AI Infrastructure

A memory system that actually knows your business.

We built a memory system that captures every conversation, picks out the people, companies, projects, and products mentioned, and connects them, so everything is findable by meaning, not just keywords.

The result: an AI assistant that remembers every client interaction, knows which project belongs to which brand, and can answer questions like "what did the natural stone client ask about last week?"

7,852
Pieces of company knowledge captured
46
People, companies & projects tracked
662
Connections mapped between them

Live counts from the memory system, refreshed continuously.

Phase 4, Agent Operations

Five AI systems. One dashboard.

The lead AI agent is connected to the tools it needs, the company memory, the project boards, the CRM, and continuously reads new conversations into that memory. Nothing depends on a single person's head anymore.

The dashboard shows every AI system at a glance: what's healthy, what's working, and what it's connected to. Here's what's running right now.

Hermes Gateway
lead AI agent, running
Company Memory
every conversation captured
Knowledge Database
secure, EU-hosted
Feature Voter
one board per brand
Connected Tools
memory, projects, CRM, search, files
Conversation Watcher
runs every 2 minutes
Phase 5, Voice Agent

AI that talks. Literally.

We deployed Dograh, an open-source voice AI platform, self-hosted on our own infrastructure. It gives each brand its own voice agent: phone-based scheduling, lead qualification, customer support. Connected to the CRM pipeline, so every call automatically creates or updates a contact.

Drag-and-drop workflow builder. No vendor lock-in. Runs on our own servers, not someone else's cloud, which means the client's call data never leaves their infrastructure.

Live, Voice Agent Platform

Dograh Voice AI Agent

Self-hosted on our NetCup server. Each brand gets its own voice agent, configured workflows, voice, and phone number. Call data never leaves your infrastructure.

Book a Voice Call

The Dograh instance is admin-only, client brands interact via phone calls routed through their configured agent.

Under the Hood

What powers this

Everything you see here runs on two servers we own in the EU, one for the AI systems, one for the client-facing services. No AWS. No enterprise subscriptions. AI capacity on a fixed monthly subscription instead of pay-per-use.

The same stack spins up for every new client. When you sign up, we don't start from scratch, we configure a proven system.

Agent Runtime Hermes, our in-house agent platform
AI Compute Fixed monthly subscription, no per-use billing
Memory Pipeline Every conversation captured and searchable
Feature Voting One board per brand, live today
CRM Shared across brands, every inquiry lands in one place
Websites Fast, secure, and German-compliant (Impressum, DSGVO)
Infrastructure Two EU servers we own and control, no big-cloud dependency
Monthly infra cost ~€80 total, servers, domains, and AI capacity included
What This Means for You

You don't start from zero.

Everything on this page, the feature voter, the memory pipeline, the agent dashboard, the CRM, is already built and running in production. When you sign up, we don't build from scratch. We configure this same stack for your brands, your clients, your data.

That's why setup is days, not months. And why we can show you a working demo on the first call.

Free Deployment Audit

Let's find the quick win.

30 minutes. No pitch. We'll scope one workflow and show you where AI runs inside your business.

© 2026 dbrd. All rights reserved.