United KingdomProfessional services2025 – ongoingMott MacDonald
EMMA internal knowledge assistant on Azure AI
Mott MacDonald's EMMA handled over 220,000 employee queries
Problem
Mott MacDonald's technical knowledge was spread across business systems. Employees spent time finding information and needed access to company-specific practices without exposing restricted data.
Approach
The company built EMMA using Microsoft Azure AI technologies and launched it on its intranet. It combined Azure AI Search with Microsoft Graph access to organisational information and employee files. Existing permissions controlled access, while safety testing and content controls addressed misuse.
Results
Takeaway
The assistant's scope depended on organised internal knowledge and existing access controls. Usage data also helped the team identify gaps in information availability.
Categories
- Size
- Large enterprise
- Industry
- Professional services
- Business function
- Internal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
Microsoft described EMMA's architecture and permission-aware retrieval of internal information. It reported over 220,000 unique employee queries and an internal reach of 60%.
Full details are in the original sources.