call_center_ai · finance · workflow
Allianz Direct improves contact center agent-assist accuracy by 10–15% with Databricks Mosaic AI
Allianz Direct's contact center agents were spending too much time on mundane back-office tasks, leaving less time for direct customer engagement. Policy questions required agents to search multiple systems and second-guess answers rather than focusing on building personal customer relationships.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Customer policy question received
Contact center agents receive customer questions about policy terms and conditions.
Tools used
Databricks Mosaic AIDatabricks Data Intelligence PlatformDatabricks NotebookAgent Bricks Custom AgentsUnity CatalogRAG
Outcome
The RAG-based agent-assist tool demonstrated a 10 to 15% accuracy uplift over the previous solution, earned agent trust, increased agent usage, and is being rolled out across all Allianz Direct contact centers.
What failed first
Allianz Direct had an existing GenAI-powered tool for contact center agents, but it was less accurate and required a more complex development and implementation process than the Databricks-based solution.
Results
Time savedspend more time talking to customers
Volume10 to 15%
Grounding & classification
Source type: vendor customer story
29 fields verified against source quotes.
agent assistknowledge searchragknowledge basepolicy documentfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedinsuranceaccuracy improvementemployee productivityvendor customer storycall center aicustomer supporthuman review queuerag answering