After-sales operating metrics
- Type
- Demonstration project
- Project
- After-sales service demonstration project
- Industry
- After-sales service
The scenario and numbers in this demonstration project are simulated data.
- Industry
- After-sales service
- What was built
- A semantic model and query tools, built on demonstration data
- Where the knowledge came from
- Demonstration data on work orders, parts stock, warranty claims and dealers
What the manager tracks
- The service manager needs each engineer's current load, the work orders about to expire and the most common failure modes.
Semantic model
- This demonstration project builds the after-sales service semantic model on the service data.
- This demonstration project has no knowledge base and no Drive. The query tools get the figures from the demonstration database.
- Once the semantic model is published to Mimir, the service manager can ask for these figures in Mimir in plain language.
- Mimir answers with figures and charts. The service manager can save the result as a report.
Query tools
- This demonstration project builds the queries as toolsets: dealer operations, after-sales service operations and quality repair work. The queries cover engineer load, work orders about to expire, failure modes, parts stock, the warranty claim outcome distribution, dealer margin and after-sales service revenue.
- These tools only read data and do not write back to any system.
Continuous improvement
- At companies like this, work orders and failure records will keep coming in.
- Feedback users give on answers will go to Odin.
- Wrong answers will become tests. A change will be kept only if scores improve.
Get started
Book a two-hour workshop
AI feasibility review of a live workflow