Hi everyone,
I’m deploying a Data Cloud/Data 360 + Prompt Builder solution from one Salesforce org to another using a package and Data Kit.
The Data Kit includes:
- Data Stream Bundle
- Case and Knowledge Data Streams
- Case and Knowledge Data Models
- Case and Knowledge Search Indexes
- Case and Knowledge Retrievers
The Data Cloud components are deployed, but my Similar Cases Prompt Template fails during deployment with:
The Prompt Template uses:
- Case Retriever
- Knowledge Retriever
Dependency:
Data Source
→ Data Streams
→ Data Models
→ Search Indexes
→ Retrievers
→ Prompt Template
My question:
What is the Salesforce-supported deployment approach for Data Cloud/Data 360 Retrievers and Prompt Builder Prompt Templates?
Do the Data Kit and all Data Cloud dependencies need to be fully deployed and available in the target org before deploying the Prompt Template?
Or can the Data Kit, Retrievers, and Prompt Template be deployed together?
Could the “cannot describe data provider”
error occur because the Retriever dependencies are not yet resolved when the Prompt Template is being validated?
Any official Salesforce documentation or practical guidance would be appreciated.
Thanks!
#Salesforce Developer #Trailhead #Sales Cloud #Data360 #Data Cloud
Great write-up of the dependency chain, and your last hypothesis is essentially right. Here is how these pieces actually deploy:
1) Supported approach for the Data Cloud foundation.
The Deploy Data Kit Components flow (or the Data Kit Publishing Sequence) is the supported way to move the core Data 360 objects. It deploys components sequentially in dependency order and waits for each component to finish before starting the next (requires REST API v61.0 or later). That covers Data Stream Bundles, Data Lake and Model Objects, Data Transforms, Calculated Insights, Data Graphs, Identity Resolution, and Segments.
2) The key catch: Retrievers, Search Indexes, and Prompt Templates are not standard Data Kit content.
They are not in the Data Kit deployable-component list, so they do not travel with the Data Stream or Model bundle. What is packageable is governed by the Data 360 Extensibility Readiness Matrix (linked on that same dev-guide page), so check it for the current status of Search Indexes and Retrievers. Prompt Templates deploy as their own metadata (GenAiPromptTemplate) through the Metadata API, packages, or change sets, separate from the Data Kit.
3) Do the dependencies need to exist first? Yes.
Your chain (Data Source, Data Streams, DMOs, Search Indexes, Retrievers, Prompt Template) has to be fully deployed and provisioned in the target before the Prompt Template validates: DMOs mapped, Search Indexes actually built, and Retrievers present and describable. Deploying the Prompt Template in the same pass as its retrievers is the risky part, because the template resolves its retriever references at deploy time.
4) The describe-data-provider error.
That lines up with what you suspected: when the Prompt Template (or the retriever it points to) is validated, its underlying data provider (the DMO, Search Index, or Retriever) is not resolvable yet in the target org, so the platform cannot describe it. Sequencing fixes it.
Recommended sequence:
1. Deploy the Data Cloud foundation via the Data Kit flow (streams, DMOs, mappings) and let it finish.
2. Create or verify the Search Indexes and Retrievers in the target and confirm they are active and queryable (rebuild indexes if needed).
3. Deploy the Prompt Template last, once its retrievers describe cleanly.
Reference: "Deploy Data Kit Components" in the Data 360 Developer Guide (
developer.salesforce.com/docs/data/data-cloud-dev). If it still will not resolve after sequencing, confirm Data Cloud is provisioned and the retriever feature is enabled in the target, since a missing provider throws the same describe error.
