A Dynamics 365 Customer Service admin has just configured the Case Management Agent to auto‑populate case fields from incoming emails and added field descriptions to help the AI make better predictions. The configuration looks right, but how will the admin ensure that the AI is able to predict case field values accurately? The new case enrichment simulation in Dynamics 365 Customer Service—now generally available—answers exactly that question.

Admins can measure AI‑powered field prediction accuracy against real organizational data before enabling case enrichment in production: test against historical records, review the results, refine field descriptions, and enable the feature when accuracy meets your bar. 

Empower admins to validate AI quality 

Case Management Agent simulations include: 

• Flexible test data — run predictions against historical case records or sample email and chat data uploaded via Excel 

• Field‑level match reports — see prediction accuracy across every field 

• Case‑level comparison view — review actual versus predicted values side by side 

• Excel export — share results offline with stakeholders 

• Re‑run capability — iterate after refining lookup field descriptions or prediction rules 

• Shadow runs — Validate predictions by activating case enrichment with live production data without writing to records. 

Run your first simulation today 

Don’t wait until production to find out how well the AI performs. Open the Copilot Service admin center, navigate to Case settings > Case Management Agent > Case creation and update > Simulation, and run your first test against historical data. Within minutes you will know exactly where to tune your field descriptions before turning on case enrichment. 

For step‑by‑step guidance, read the documentation: 

• Set up Case Management Agent | Microsoft Learn 

The post Run case enrichment simulation to assess AI prediction quality in Dynamics 365 Customer Service  appeared first on Microsoft Dynamics 365 Blog.