Case Studies / Leading Automotive Manufacturer
AUTOMOTIVE · PRODUCTION PLANNING
Replacing manual data lookups with an AI planning assistant
Product planners at a leading luxury car manufacturer spent hours manually querying SAP BW and multiple data warehouses to get the numbers they needed. We built a conversational AI assistant that retrieves planning data on demand – in German or English, via text or voice – connected securely to their on-premise SAP systems.
Client: Leading global luxury car manufacturer (under NDA) – one of the world’s largest premium automotive companies.
KEY RESULTS
Hours→sec
Planning data retrieval time per query
2 langs
Full German and English voice + text support
On-prem
Secure hybrid connection – data never leaves client infrastructure
Self-serve
Planners query complex data without IT support
INDUSTRY
Automotive
USE CASE
Planning data retrieval & querying
AI APPROACH
NLP / NLU, conversational AI
SYSTEMS
SAP BW, internal data warehouses
INFRASTRUCTURE
Microsoft Azure + on-premise hybrid
ENGAGEMENT
Design thinking → Agile delivery
The challenge
Car product planning is one of the most data-intensive processes in automotive manufacturing. At this company, planners needed to pull data from SAP BW and several other internal data warehouses to make decisions – production volumes, configuration options, market-specific variants, scheduling constraints.
The problem wasn’t that the data didn’t exist. It was that getting to it required specialist knowledge of the underlying systems. Planners had to know which data warehouse held what, how to navigate SAP BW’s query structures, and how to cross-reference information across multiple sources. In practice, every planning question turned into a manual research exercise – or a request to someone else who knew the systems better.
The core problem: planning data was scattered across SAP BW and multiple warehouses. Every query required specialist system knowledge, turning routine data retrieval into a slow, manual process that consumed hours of planner time daily.
What we built
We started with design thinking workshops to understand how planners actually worked – what questions they asked, what data they needed, where the manual bottlenecks were. This shaped the solution directly.
Conversational AI interface. We built an intelligent assistant that planners could query in natural language – typed or spoken, in German or English. Instead of navigating SAP BW transactions or writing queries, a planner could simply ask a question in plain language and get the answer immediately.
Multi-system data retrieval. Behind the conversational interface, the assistant connected to SAP BW and the company’s other planning data warehouses. It understood the logic of the underlying data structures – which system held which information, how to combine data from multiple sources – and handled the complexity that planners previously had to manage themselves.
Hybrid cloud architecture. The company’s planning data had to stay on-premise – non-negotiable for an automotive manufacturer of this scale. We built the AI assistant in Microsoft Azure while establishing a secure connection to the on-premise SAP infrastructure. Strict permission controls ensured the assistant only accessed data the specific user was authorized to see.
Bilingual voice and text. Using NLP and NLU capabilities, the assistant handled both German and English fluently – in written and spoken form. Planners across different locations and teams could interact in whichever language was natural to them.
The solution was built using Microsoft Azure cloud-native services – LUIS for language understanding, Bot Service for the conversational layer, CosmosDB for session data, and AppService for deployment – and delivered in agile sprints with continuous stakeholder involvement through the client’s IT department.
The results
BEFORE
Planners manually queried SAP BW and multiple data warehouses. Each data request required specialist knowledge or IT support. Routine questions took hours to answer.
AFTER
Planners ask questions in plain language and get answers in seconds. No system expertise required. Data retrieval happens automatically across all connected sources.
The manual work of navigating data systems was eliminated for routine planning queries. Planners who previously spent significant time pulling and cross-referencing data could now focus on actually making planning decisions – the work they were hired to do.
The hybrid architecture proved that enterprise AI doesn’t require moving sensitive data to the cloud. The company kept full control over their planning data while giving their teams a modern, intuitive way to access it.
The project also demonstrated a pattern we see frequently in enterprise environments: the biggest efficiency gains don’t come from replacing people, but from removing the manual overhead that prevents skilled professionals from doing their actual work.
Technology used
More Case Studies
See how we’ve helped other companies
AUTOMOTIVE (UNDER NDA)
Replacing reactive maintenance with a predictive maintenance roadmap
Unplanned equipment failures were causing costly production stops. We assessed the manufacturer’s infrastructure and delivered a concrete architecture for predictive maintenance, a roadmap from reactive repairs to data-driven prevention.
PdM
Architecture
Roadmap
Delivered
MANUFACTURING · RADAWAY
Making email-based order processing reliable with LLMs
Staff were manually reading customer emails, identifying products, and entering orders by hand. We turned a promising AI prototype into a production system that handles it end to end, across languages, formats, and attachments.
-90%
Manual intervention
95%+
Match accuracy
LOGISTICS · FR. MEYER’S SOHN
Eliminating manual data extraction from thousands of daily shipping emails
Operations staff were manually reading German and English logistics emails to pull out routing and scheduling data, every single day. We built an AI pipeline that extracts, structures, and delivers the data automatically.
–80%
Manual effort
2 langs
DE & EN
On-prem
Deployed