Data 360 for Complaint Management Assistance
Understand how Data 360 powers Complaint Management Assistance by grounding the agent in your historical complaint records.
Required Editions
| Available in: Lightning Experience |
| Available in: Professional, Enterprise, and Unlimited Editions with the Agentforce for Financial Services add-on license or included in Agentforce 1 Financial Services Edition. Requires each user to have the Agentforce for Financial Services add-on to access the action. |
Data 360 serves as the knowledge base for the Complaint Management Assistance agent. Rather than relying on external models, the agent uses your structured complaint data to ground its responses. When complaint handlers ask the agent to analyze a current issue, identify patterns, or draft customer responses, the agent references this connected data to surface relevant resolution strategies.
Data Streams for Public Complaints
A data stream acts as the automated pipeline between your Salesforce CRM platform and Data 360. By establishing this pipeline specifically for the Public Complaint object, you make sure that every new complaint submission and a record update flows directly into the agent’s knowledge base. When a complaint handler asks the agent for historical insights, the agent evaluates recent organizational data rather than outdated information.
Data Lake Object Mapping
When ingesting complaint records from your CRM, you should map their native fields to a target Data Model Object (DMO) in Data 360. This mapping process helps the agent distinguish the customer’s initial problem from the final resolution. By defining what each piece of data means, you prevent the agent from confusing a customer’s initial report with the outcome when it searches for historical matches.
Search Indexes
A search index transforms text fields into a format that the agent can analyze and evaluate. By using a search approach, the index breaks down complaint details into smaller pieces, or chunks. With this setup, the agent performs both keyword matches and semantic matches based on intent. When a complaint handler asks the agent about a specific issue, the index returns relevant past complaints even if the handler uses different words.
Data Libraries
A data library serves as the knowledge container that connects your historical complaint data to the agent. After the data stream, Data Model Object (DMO), and search index are in place, you manually create a data library as the final step. By attaching this data library to the Complaint Management Assistance agent, you give the agent a direct reference point for historical complaint data.
